Tootfinder

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Tianqi Zhong, Zhaoyi Li, Quan Wang, Linqi Song, Ying Wei, Defu Lian, Zhendong Mao
https://arxiv.org/abs/2404.04232

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods. Nonetheless, a comprehensive compositional generalization evaluation benchmark of MCTG is still lacking. We propose CompMCTG, a benchmark encompassing diverse multi-aspect labeled datasets and a crafted three-dimensional evaluation proto…

Convolutional Neural Network Transformer (CNNT) for Fluorescence Microscopy image Denoising with Improved Generalization and Fast Adaptation
Azaan Rehman, Alexander Zhovmer, Ryo Sato, Yosuke Mukoyama, Jiji Chen, Alberto Rissone, Rosa Puertollano, Harshad Vishwasrao, Hari Shroff, Christian A. Combs, Hui Xue
https://arxiv.org/abs/…

Convolutional Neural Network Transformer (CNNT) for Fluorescence Microscopy image Denoising with Improved Generalization and Fast Adaptation
Deep neural networks have been applied to improve the image quality of fluorescence microscopy imaging. Previous methods are based on convolutional neural networks (CNNs) which generally require more time-consuming training of separate models for each new imaging experiment, impairing the applicability and generalization. Once the model is trained (typically with tens to hundreds of image pairs) it can then be used to enhance new images that are like the training data. In this study, we propose…

A generalization of concise words
Costantino Delizia, Michele Gaeta, Carmine Monetta
https://arxiv.org/abs/2404.06308 https://arxiv.o…

A generalization of concise words
The study of verbal subgroups within a group is well-known for being an effective tool to obtain structural information about a group. Therefore, conditions that allow the classification of words in a free group are of paramount importance. One of the most studied problems is to establish which words are concise, where a word $w$ is said to be concise if the verbal subgroup $w(G)$ is finite in each group $G$ in which $w$ takes only a finite number of values. The purpose of this article is to …

This https://arxiv.org/abs/2403.13245 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Federated reinforcement learning for robot motion planning with zero-shot generalization
This paper considers the problem of learning a control policy for robot motion planning with zero-shot generalization, i.e., no data collection and policy adaptation is needed when the learned policy is deployed in new environments. We develop a federated reinforcement learning framework that enables collaborative learning of multiple learners and a central server, i.e., the Cloud, without sharing their raw data. In each iteration, each learner uploads its local control policy and the correspon…

This https://arxiv.org/abs/2309.13539 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

MediViSTA-SAM: Zero-shot Medical Video Analysis with Spatio-temporal SAM Adaptation for Echocardiography
The Segmentation Anything Model (SAM) has gained significant attention for its robust generalization capabilities across diverse downstream tasks. However, the performance of SAM is noticeably diminished in medical images due to the substantial disparity between natural and medical image domain. In this paper, we present a zero-shot generalization model specifically designed for echocardiography analysis, called MediViSTA-SAM. Our key components include (i) the introduction of frame-level self-…

Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction
Jinyuan Feng, Min Chen, Zhiqiang Pu, Tenghai Qiu, Jianqiang Yi
https://arxiv.org/abs/2404.05950

Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction
Multi-task reinforcement learning (MTRL) demonstrate potential for enhancing the generalization of a robot, enabling it to perform multiple tasks concurrently. However, the performance of MTRL may still be susceptible to conflicts between tasks and negative interference. To facilitate efficient MTRL, we propose Task-Specific Action Correction (TSAC), a general and complementary approach designed for simultaneous learning of multiple tasks. TSAC decomposes policy learning into two separate polic…

The Church Synthesis Problem over Continuous Time
Alexander Rabinovich, Daniel Fattal
https://arxiv.org/abs/2404.04782 https://arxiv.…

The Church Synthesis Problem over Continuous Time
The Church Problem asks for the construction of a procedure which, given a logical specification A(I,O) between input omega-strings I and output omega-strings O, determines whether there exists an operator F that implements the specification in the sense that A(I, F(I)) holds for all inputs I. Buchi and Landweber provided a procedure to solve the Church problem for MSO specifications and operators computable by finite-state automata. We investigate a generalization of the Church synthesis probl…

An algebraic generalization of the entropy and its application to statistics
Martin Schlather
https://arxiv.org/abs/2404.05854 https://

An algebraic generalization of the entropy and its application to statistics
We define a general notion of entropy in elementary, algebraic terms. Based on that, weak forms of a scalar product and a distance measure are derived. We give basic properties of these quantities, generalize the Cauchy-Schwarz inequality, and relate our approach to the theory of scoring rules. Many supporting examples illustrate our approach and give new perspectives on established notions, such as the likelihood, the Kullback-Leibler divergence, the uncorrelatedness of random variables, the s…

Composable Part-Based Manipulation
Weiyu Liu, Jiayuan Mao, Joy Hsu, Tucker Hermans, Animesh Garg, Jiajun Wu
https://arxiv.org/abs/2405.05876 https://

Composable Part-Based Manipulation
In this paper, we propose composable part-based manipulation (CPM), a novel approach that leverages object-part decomposition and part-part correspondences to improve learning and generalization of robotic manipulation skills. By considering the functional correspondences between object parts, we conceptualize functional actions, such as pouring and constrained placing, as combinations of different correspondence constraints. CPM comprises a collection of composable diffusion models, where each…

Kripke-like models of Set Theory in Modal Residuated Logic
Jose Moncayo, Pedro H. Zambrano
https://arxiv.org/abs/2405.04641 https://a…

Kripke-like models of Set Theory in Modal Residuated Logic
We generalize Fitting's work on Intuitionistic Kripke models of Set Theory using Ono and Komori's Residuated Kripke models. Based on these models, we provide a generalization of the von Neumann hierarchy in the context of Modal Residuated Logic and prove a translation of formulas between it and a suited Heyting valued model. We also propose a notion of universe of constructible sets in Modal Residuated Logic and discuss some aspects of it.

This https://arxiv.org/abs/2402.14095 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Zero-shot generalization across architectures for visual classification
Generalization to unseen data is a key desideratum for deep networks, but its relation to classification accuracy is unclear. Using a minimalist vision dataset and a measure of generalizability, we show that popular networks, from deep convolutional networks (CNNs) to transformers, vary in their power to extrapolate to unseen classes both across layers and across architectures. Accuracy is not a good predictor of generalizability, and generalization varies non-monotonically with layer depth.

Instance-Conditioned Adaptation for Large-scale Generalization of Neural Combinatorial Optimization
Changliang Zhou, Xi Lin, Zhenkun Wang, Xialiang Tong, Mingxuan Yuan, Qingfu Zhang
https://arxiv.org/abs/2405.01906

Instance-Conditioned Adaptation for Large-scale Generalization of Neural Combinatorial Optimization
The neural combinatorial optimization (NCO) approach has shown great potential for solving routing problems without the requirement of expert knowledge. However, existing constructive NCO methods cannot directly solve large-scale instances, which significantly limits their application prospects. To address these crucial shortcomings, this work proposes a novel Instance-Conditioned Adaptation Model (ICAM) for better large-scale generalization of neural combinatorial optimization. In particular, …

Generalization of the Alpha-Stable Distribution with the Degree of Freedom
Stephen H. Lihn
https://arxiv.org/abs/2405.04693 https://a…

Generalization of the Alpha-Stable Distribution with the Degree of Freedom
A Wright function based framework is proposed to combine and extend several distribution families. The $α$-stable distribution is generalized by adding the degree of freedom parameter. The PDF of this two-sided super distribution family subsumes those of the original $α$-stable, Student's t distributions, as well as the exponential power distribution and the modified Bessel function of the second kind. Its CDF leads to a fractional extension of the Gauss hypergeometric function. The degree of…

Ky Fan theorem for sphere bundles
Gaiane Panina, Rade \v{Z}ivaljevi\'c
https://arxiv.org/abs/2404.04806 https://arxiv.org/pdf/240…

Ky Fan theorem for sphere bundles
The classic Ky Fan theorem is a combinatorial equivalent of Borsuk-Ulam theorem. It is a generalization and extension of Tucker's lemma and, just like its predecessor, it pinpoints important properties of antipodal colorings of vertices of a triangulated sphere $S^n$. Here we describe generalizations of Ky Fan theorem for the case when the sphere is replaced by the total space of a triangulated sphere bundle.

This https://arxiv.org/abs/2404.15867 has been replaced.
link: https://scholar.google.com/scholar?q=a

A Generalization of Relative Entropy to Count Vectors and its Concentration Property
We introduce a new generalization of relative entropy to non-negative vectors with sums $\gt 1$. We show in a purely combinatorial setting, with no probabilistic considerations, that in the presence of linear constraints defining a convex polytope, a concentration phenomenon arises for this generalized relative entropy, and we quantify the concentration precisely. We also present a probabilistic formulation, and extend the concentration results to it. In addition, we provide a number of simplif…

AttacKG :Boosting Attack Knowledge Graph Construction with Large Language Models
Yongheng Zhang, Tingwen Du, Yunshan Ma, Xiang Wang, Yi Xie, Guozheng Yang, Yuliang Lu, Ee-Chien Chang
https://arxiv.org/abs/2405.04753

AttacKG+:Boosting Attack Knowledge Graph Construction with Large Language Models
Attack knowledge graph construction seeks to convert textual cyber threat intelligence (CTI) reports into structured representations, portraying the evolutionary traces of cyber attacks. Even though previous research has proposed various methods to construct attack knowledge graphs, they generally suffer from limited generalization capability to diverse knowledge types as well as requirement of expertise in model design and tuning. Addressing these limitations, we seek to utilize Large Language…

This https://arxiv.org/abs/2402.10498 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A higher genus circle method and an application to geometric Manin's conjecture
Browning and Vishe used the Hardy-Littlewood circle method to show the moduli space of rational curves on smooth hypersurfaces of low degree is irreducible and of the expected dimension. We reinterpret the circle method geometrically and prove a generalization for higher genus smooth projective curves. In particular, we explain how the geometry of numbers can be understood via the Beauville-Laszlo theorem in terms of vector bundles on curves and their slopes, allowing us to prove a higher genus…

$f(R,\square R)$-gravity and equivalency with the modified GUP Scalar field models
Andronikos Paliathanasis
https://arxiv.org/abs/2404.04519 https://

$f(R,\square R)$-gravity and equivalency with the modified GUP Scalar field models
Inspired by the generalization of scalar field gravitational models with a minimum length we study the equivalent theory in modified theories of gravity. The quadratic Generalized Uncertainty Principle (GUP) gives rise to a deformed Heisenberg algebra in the application, resulting in the emergence of additional degrees of freedom described by higher-order derivatives. The new degrees of freedom can be attributed to the introduction of a new scalar field, trasforming the resulting theory into a …

This https://arxiv.org/abs/2308.16702 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Degenerations Of Skein Algebras And Quantum Traces
We introduce a joint generalization, called LRY skein algebras, of Kauffman bracket skein algebras (of surfaces) that encompasses both Roger-Yang skein algebras and stated skein algebras. We will show that, over an arbitrary ground ring which is a commutative domain, the LRY skein algebras are domains and have degenerations (by filtrations) equal to monomial subalgebras of quantum tori. For surfaces without interior punctures, this integrality generalizes a result of Moon and Wong to the most g…

Quantized $p$-form Gauge Field in D-dimensional de Sitter Spacetime
E. W. D. Dantas, G. Alencar, I. Guedes, Milko Estrada
https://arxiv.org/abs/2404.05751 …

Quantized $p$-form Gauge Field in D-dimensional de Sitter Spacetime
In this work, we utilize the dynamic invariant method to obtain a solution for the time-dependent Schrödinger equation, aiming to explore the quantum theory of a $p$-form gauge field propagating in $D$-dimensional de Sitter spacetimes. Thus, we present a generalization, through the use of $p$-form gauge fields, of the quantization procedure for the scalar, electromagnetic, and Kalb-Ramond fields, all of which have been previously studied in the literature. We present an exact solution for the …

This https://arxiv.org/abs/2306.16323 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Jacobi Beta Ensemble and $b$-Hurwitz Numbers
We express correlators of the Jacobi $β$ ensemble in terms of (a special case of) $b$-Hurwitz numbers, a deformation of Hurwitz numbers recently introduced by Chapuy and Dolega. The proof relies on Kadell's generalization of the Selberg integral. The Laguerre limit is also considered. All the relevant $b$-Hurwitz numbers are interpreted (following Bonzom, Chapuy, and Dolega) in terms of colored monotone Hurwitz maps.

Federated Adaptation for Foundation Model-based Recommendations
Chunxu Zhang, Guodong Long, Hongkuan Guo, Xiao Fang, Yang Song, Zhaojie Liu, Guorui Zhou, Zijian Zhang, Yang Liu, Bo Yang
https://arxiv.org/abs/2405.04840

Federated Adaptation for Foundation Model-based Recommendations
With the recent success of large language models, particularly foundation models with generalization abilities, applying foundation models for recommendations becomes a new paradigm to improve existing recommendation systems. It becomes a new open challenge to enable the foundation model to capture user preference changes in a timely manner with reasonable communication and computation costs while preserving privacy. This paper proposes a novel federated adaptation mechanism to enhance the foun…

This https://arxiv.org/abs/2311.18601 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

A method for multi-leader-multi-follower games by smoothing the followers' response function
The multi-leader--multi-follower game (MLMFG) involves two or more leaders and followers and serves as a generalization of the Stackelberg game and the single-leader--multi-follower game (SLMFG). Although MLMFG covers wide range of real-world applications, its research is still sparse. Notably, fundamental solution methods for this class of problems remain insufficiently established. A prevailing approach is to recast the MLMFG as an equilibrium problem with equilibrium constraints (EPEC) and s…

Higher Berry Connection for Matrix Product States
Shuhei Ohyama, Shinsei Ryu
https://arxiv.org/abs/2405.05327 https://arxiv.org/pdf/2…

Higher Berry Connection for Matrix Product States
In one spatial dimension, families of short-range entangled many-body quantum states, parameterized over some parameter space, can be topologically distinguished and classified by topological invariants built from the higher Berry phase -- a many-body generalization of the Berry phase. Previous works identified the underlying mathematical structure (the gerbe structure) and introduced a multi-wavefunction overlap, a generalization of the inner product in quantum mechanics, which allows for the …

This https://arxiv.org/abs/2112.09849 has been replaced.
link: https://scholar.google.com/scholar?q=a

Strongly Lech-independent ideals and Lech's conjecture
We introduce the notion of strongly Lech-independent ideals as a generalization of Lech-independent ideals defined by Lech and Hanes, and use this notion to derive inequalities on multiplicities of ideals. In particular we prove that if $(R,\mathfrak{m}) \to (S,\mathfrak{n})$ is a flat local extension of local rings with $\dim R = \dim S$, the completion of $S$ is the completion of a standard graded ring over a field $k$ with respect to the homogeneous maximal ideal, and the completion of $\mat…

Understanding LLMs Requires More Than Statistical Generalization
Patrik Reizinger, Szilvia Ujv\'ary, Anna M\'esz\'aros, Anna Kerekes, Wieland Brendel, Ferenc Husz\'ar
https://arxiv.org/abs/2405.01964

Understanding LLMs Requires More Than Statistical Generalization
The last decade has seen blossoming research in deep learning theory attempting to answer, "Why does deep learning generalize?" A powerful shift in perspective precipitated this progress: the study of overparametrized models in the interpolation regime. In this paper, we argue that another perspective shift is due, since some of the desirable qualities of LLMs are not a consequence of good statistical generalization and require a separate theoretical explanation. Our core argument relies on the…

Sobolev mappings on metric spaces and Minkowski dimension
Efstathios Konstantinos Chrontsios Garitsis
https://arxiv.org/abs/2405.05172 https://

Sobolev mappings on metric spaces and Minkowski dimension
We introduce the class of compactly Hölder mappings between metric spaces and determine the extent to which they distort the Minkowski dimension of a given set. These mappings are defined purely with metric notions and can be seen as a generalization of Sobolev mappings, without the requirement for a measure on the source space. In fact, we show that if $f:X\rightarrow Y$ is a continuous mapping lying in some super-critical Newtonian-Sobolev space $N^{1,p}(X,μ)$, under standard assumptions on…

This https://arxiv.org/abs/2201.09754 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deep Reinforcement Learning with Spiking Q-learning
With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (RL). There are only a few existing SNN-based RL methods at present. Most of them either lack generalization ability or employ Artificial Neural Networks (ANNs) to estimate value function in training. The former n…

Understanding High-Order Network Structure using Permissible Walks on Attributed Hypergraphs
Enzo Battistella, Sean English, Robert Green, Cliff Joslyn, Evgeniya Lagoda, Van Magnan, Audun Myers, Evan D. Nash, Michael Robinson
https://arxiv.org/abs/2405.04559

Understanding High-Order Network Structure using Permissible Walks on Attributed Hypergraphs
Hypergraphs have been a recent focus of study in mathematical data science as a tool to understand complex networks with high-order connections. One question of particular relevance is how to leverage information carried in hypergraph attributions when doing walk-based techniques. In this work, we focus on a new generalization of a walk in a network that recovers previous approaches and allows for a description of permissible walks in hypergraphs. Permissible walk graphs are constructed by inte…

This https://arxiv.org/abs/2307.13660 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCG_…

Computing the Gromov--Hausdorff distance using gradient methods
The Gromov--Hausdorff distance measures the difference in shape between metric spaces and poses a notoriously difficult problem in combinatorial optimization. We introduce its quadratic relaxation over a convex polytope whose solutions provably deliver the Gromov--Hausdorff distance. The optimality guarantee is enabled by the fact that the search space of our approach is not constrained to a generalization of bijections, unlike in other relaxations such as the Gromov--Wasserstein distance. We…

Perspective on Physical Interpretations of R\'enyi Entropy in Statistical Mechanics
Misaki Ozawa, Nina Javerzat
https://arxiv.org/abs/2404.06436 https:…

Perspective on Physical Interpretations of Rényi Entropy in Statistical Mechanics
Rényi entropy is a one-parameter generalization of Shannon entropy, which has been used in various fields of physics. Despite its wide applicability, the physical interpretations of the Rényi entropy are not widely known. In this paper, we discuss some basic properties of the Rényi entropy relevant to physics, in particular statistical mechanics, and its physical interpretations using free energy, replicas, work, and large deviation.

This https://arxiv.org/abs/2309.09371 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Gibbs Sampling using Anti-correlation Gaussian Data Augmentation, with Applications to L1-ball-type Models
L1-ball-type priors are a recent generalization of the spike-and-slab priors. By transforming a continuous precursor distribution to the L1-ball boundary, it induces exact zeros with positive prior and posterior probabilities. With great flexibility in choosing the precursor and threshold distributions, we can easily specify models under structured sparsity, such as those with dependent probability for zeros and smoothness among the non-zeros. Motivated to significantly accelerate the posterior…

CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as Teachers
Lakshmi Nair
https://arxiv.org/abs/2404.06170 https://<…

CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as Teachers
Contrastive Language-Image Pre-training (CLIP) has been shown to improve zero-shot generalization capabilities of language and vision models. In this paper, we extend CLIP for efficient knowledge distillation, by utilizing embeddings as teachers. Typical knowledge distillation frameworks require running forward passes through a teacher model, which is often prohibitive in the case of billion or trillion parameter teachers. In these cases, using only the embeddings of the teacher models to guide…

Geometry of infinite dimensional Cartan Developments
Johanna Michor, Peter W. Michor
https://arxiv.org/abs/2404.05416 https://arxiv.o…

Geometry of infinite dimensional Cartan Developments
The Cartan development takes a Lie algebra valued 1-form satisfying the Maurer-Cartan equation on a simply connected manifold $M$ to a smooth mapping from $M$ into the Lie group. In this paper this is generalized to infinite dimensional $M$ for infinite dimensional regular Lie groups. The Cartan development is viewed as a generalization of the evolution map of a regular Lie group. The tangent mapping of a Cartan development is identified as another Cartan development.

On a generalization of R. Chapman's "evil determinant"
Li-Yuan Wang, Hai-Liang Wu, He-Xia Ni
https://arxiv.org/abs/2405.02112 https://…

On a generalization of R. Chapman's "evil determinant"
Let $p$ be an odd prime and $x$ be an indeterminate. Recently, Z.-W. Sun proposed the following conjecture: $$\det\left[x+\left(\frac{j-i}{p}\right)\right]_{0\le i,j\le \frac{p-1}{2}}=\begin{cases} (\frac{2}{p})pb_px-a_p & \mbox{if}\ p\equiv 1\pmod4, 1 & \mbox{if}\ p\equiv 3\pmod4, \end{cases}$$ where $a_p$ and $b_p$ are rational numbers related to the fundamental unit and class number of the real quadratic field $\mathbb{Q}(\sqrt{p})$. In this paper, we confirm the above conjecture of Sun base…

The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models
Adithya Bhaskar, Dan Friedman, Danqi Chen
https://arxiv.org/abs/2403.03942

The Heuristic Core: Understanding Subnetwork Generalization in Pretrained Language Models
Prior work has found that pretrained language models (LMs) fine-tuned with different random seeds can achieve similar in-domain performance but generalize differently on tests of syntactic generalization. In this work, we show that, even within a single model, we can find multiple subnetworks that perform similarly in-domain, but generalize vastly differently. To better understand these phenomena, we investigate if they can be understood in terms of "competing subnetworks": the model initially …

Finite Sample Analysis and Bounds of Generalization Error of Gradient Descent in In-Context Linear Regression
Karthik Duraisamy
https://arxiv.org/abs/2405.02462

Finite Sample Analysis and Bounds of Generalization Error of Gradient Descent in In-Context Linear Regression
Recent studies show that transformer-based architectures emulate gradient descent during a forward pass, contributing to in-context learning capabilities - an ability where the model adapts to new tasks based on a sequence of prompt examples without being explicitly trained or fine tuned to do so. This work investigates the generalization properties of a single step of gradient descent in the context of linear regression with well-specified models. A random design setting is considered and anal…

Cross-Domain Audio Deepfake Detection: Dataset and Analysis
Yuang Li, Min Zhang, Mengxin Ren, Miaomiao Ma, Daimeng Wei, Hao Yang
https://arxiv.org/abs/2404.04904

Cross-Domain Audio Deepfake Detection: Dataset and Analysis
Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance. However, the existing ADD datasets are outdated, leading to suboptimal generalization of detection models. In this paper, we construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zero…

This https://arxiv.org/abs/2309.15005 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Sharp conditions for exponential and non-exponential uniform stabilization of the time-dependent damped wave equation
It is classical that uniform stabilization of solutions to the autonomous damped wave equation is equivalent to every geodesic meeting the positive set of the damping, which is called the geometric control condition. In this paper, it is shown that for time-dependent damping, a generalization of the geometric control condition is equivalent to uniform stabilization at an exponential rate. Additionally, non-exponential uniform stabilization rates are computed for damping which do not satisfy thi…

This https://arxiv.org/abs/2311.11871 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Training robust and generalizable quantum models
Adversarial robustness and generalization are both crucial properties of reliable machine learning models. In this letter, we study these properties in the context of quantum machine learning based on Lipschitz bounds. We derive parameter-dependent Lipschitz bounds for quantum models with trainable encoding, showing that the norm of the data encoding has a crucial impact on the robustness against data perturbations. Further, we derive a bound on the generalization error which explicitly involve…

This https://arxiv.org/abs/2310.04781 has been replaced.
link: https://scholar.google.com/scholar?q=a

Unifying Foundation Models with Quadrotor Control for Visual Tracking Beyond Object Categories
Visual control enables quadrotors to adaptively navigate using real-time sensory data, bridging perception with action. Yet, challenges persist, including generalization across scenarios, maintaining reliability, and ensuring real-time responsiveness. This paper introduces a perception framework grounded in foundation models for universal object detection and tracking, moving beyond specific training categories. Integral to our approach is a multi-layered tracker integrated with the foundation …

This https://arxiv.org/abs/2405.00363 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Competing bootstrap processes on the random graph $G(n,p)$
We consider a generalization of classic bootstrap percolation in which two competing processes concurrently evolve on the same graph $G(n,p)$. Nodes can be in one of three states, conveniently represented by different colors: red, black and white. Initially, a given number $a_R$ of active red nodes (red seeds) are selected uniformly at random among the $n$ nodes. Similarly, a given number $a_B$ of active black nodes (black seeds) are selected uniformly at random among the other $n-a_R$ nodes. A…

Generalization of Ramanujan Famous Nested Radicals to the nth Root and their Evaluation
Narendranath Mitra
https://arxiv.org/abs/2404.04051 https://…

Generalization of Ramanujan Famous Nested Radicals to the nth Root and their Evaluation
Srinivasa Ramanujan posed a problem on infinite nested radical of the square root in the Journal of Indian Mathematical Society in 1911. He had generated the problem years before in the form of an example illustrating a more general theorem. Of course, how we would figure the solution out without Ramanujan theorem was scarcely obvious. Generation of infinite nested radicals, the roots being of higher order i.e. proceeding from the cube roots to the nth root as well as their evaluation may seem …

This https://arxiv.org/abs/2206.06839 has been replaced.
link: https://scholar.google.com/scholar?q=a

Filtrations and torsion pairs in Abramovich Polishchuk's heart
We study some abelian subcategories and torsion pairs in Abramovich Polishchuk's heart. And we construct stability conditions on a full triangulated subcategory $\mathcal{D}^{\leq 1}_S$ in $D(X\times S)$, for an arbitrary smooth projective variety S. We also define a notion of $l$-th level stability, which is a generalization of the slope stability and the Gieseker stability. We show that for any object E in Abramovich Polishchuk's heart, there is a unique filtration whose factors are $l$-th le…

This https://arxiv.org/abs/2302.04164 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

(-1)-Enumerations of arrowed Gelfand-Tsetlin patterns
Arrowed Gelfand-Tsetlin patterns have recently been introduced to study alternating sign matrices. In this paper, we show that a $(-1)$-enumeration of arrowed Gelfand-Tsetlin patterns can be expressed by a simple product formula. The numbers are a one-parameter generalization of the numbers $2^{n(n-1)/2} \prod_{j=0}^{n-1} \frac{(4j+2)!}{(n+2j+1)!}$ that appear in recent work of Di Francesco. A second result concerns the (-1)-enumeration of arrowed Gelfand-Tsetlin patterns when excluding double-…

Raney extensions of frames: algebraic aspects
Anna Laura Suarez
https://arxiv.org/abs/2405.02990 https://arxiv.org/pdf/2405.02990

Raney extensions of frames: algebraic aspects
We draw from Raney duality and generalize the notion of canonical extension for distributive lattices to the context of frames. This is a generalization because for distributive lattices we are in the context of coherent spaces, whereas frames represent arbitrary spaces. We introduce Raney extensions of frames, pairs $(L,C)$ where $C$ is a coframe, $L\subseteq C$ is a frame that meet-generates it, and the inclusion $L\subseteq C$ preserves the frame operations as well as the strongly exact meet…

Prize-Collecting Steiner Tree: A 1.79 Approximation
Ali Ahmadi, Iman Gholami, MohammadTaghi Hajiaghayi, Peyman Jabbarzade, Mohammad Mahdavi
https://arxiv.org/abs/2405.03792

Prize-Collecting Steiner Tree: A 1.79 Approximation
Prize-Collecting Steiner Tree (PCST) is a generalization of the Steiner Tree problem, a fundamental problem in computer science. In the classic Steiner Tree problem, we aim to connect a set of vertices known as terminals using the minimum-weight tree in a given weighted graph. In this generalized version, each vertex has a penalty, and there is flexibility to decide whether to connect each vertex or pay its associated penalty, making the problem more realistic and practical. Both the Steiner …

Teacher-Student Network for Real-World Face Super-Resolution with Progressive Embedding of Edge Information
Zhilei Liu, Chenggong Zhang
https://arxiv.org/abs/2405.04778

Teacher-Student Network for Real-World Face Super-Resolution with Progressive Embedding of Edge Information
Traditional face super-resolution (FSR) methods trained on synthetic datasets usually have poor generalization ability for real-world face images. Recent work has utilized complex degradation models or training networks to simulate the real degradation process, but this limits the performance of these methods due to the domain differences that still exist between the generated low-resolution images and the real low-resolution images. Moreover, because of the existence of a domain gap, the seman…

Quantum Circuit $C^*$-algebra Net
Yuka Hashimoto, Ryuichiro Hataya
https://arxiv.org/abs/2404.06218 https://arxiv.org/pdf/2404.06218<…

Quantum Circuit $C^*$-algebra Net
This paper introduces quantum circuit $C^*$-algebra net, which provides a connection between $C^*$-algebra nets proposed in classical machine learning and quantum circuits. Using $C^*$-algebra, a generalization of the space of complex numbers, we can represent quantum gates as weight parameters of a neural network. By introducing additional parameters, we can induce interaction among multiple circuits constructed by quantum gates. This interaction enables the circuits to share information among…

End-to-end training of Multimodal Model and ranking Model
Xiuqi Deng, Lu Xu, Xiyao Li, Jinkai Yu, Erpeng Xue, Zhongyuan Wang, Di Zhang, Zhaojie Liu, Guorui Zhou, Yang Song, Na Mou, Shen Jiang, Han Li
https://arxiv.org/abs/2404.06078

End-to-end training of Multimodal Model and ranking Model
Traditional recommender systems heavily rely on ID features, which often encounter challenges related to cold-start and generalization. Modeling pre-extracted content features can mitigate these issues, but is still a suboptimal solution due to the discrepancies between training tasks and model parameters. End-to-end training presents a promising solution for these problems, yet most of the existing works mainly focus on retrieval models, leaving the multimodal techniques under-utilized. In thi…

On Linear Codes Whose Hermitian Hulls are MD
Gaojun Luo, Lin Sok, Martianus Frederic Ezerman, San Ling
https://arxiv.org/abs/2404.04993 https://

On Linear Codes Whose Hermitian Hulls are MD
Hermitian hulls of linear codes are interesting for theoretical and practical reasons alike. In terms of recent application, linear codes whose hulls meet certain conditions have been utilized as ingredients to construct entanglement-assisted quantum error correcting codes. This family of quantum codes is often seen as a generalization of quantum stabilizer codes. Theoretically, compared with the Euclidean setup, the Hermitian case is much harder to deal with. Hermitian hulls of MDS linear code…

Generalization of Einstein's gravitational field equations
Fr\'ed\'eric Moulin
https://arxiv.org/abs/2405.03698 https://a…

Generalization of Einstein's gravitational field equations
The Riemann tensor is the cornerstone of general relativity, but as everyone knows it does not appear explicitly in Einstein's equation of gravitation. This suggests that the latter may not be the most general equation. We propose here for the first time, following a rigorous mathematical treatment based on the variational principle, that there exists a generalized 4-index gravitational field equation containing the Riemann curvature tensor linearly, and thus the Weyl tensor as well. We show th…

Generalization of composite dynamics for the lattice Boltzmann method
Julius Weinmiller, Benjamin Kellers, Martin P. Lautenschlaeger, Timo Danner, Arnulf Latz
https://arxiv.org/abs/2403.03042

Generalization of composite dynamics for the lattice Boltzmann method
A generalized composite dynamics (GCD) framework is presented for the lattice Boltzmann method (LBM). It leverages synergies of various simple collision operators to model complex physical processes. The framework is validated by recovering semi-permeable fluid flow methods. It provides mathematical justification for the incorporation of forces, addressing a gap in the literature. The versatility of this framework is demonstrated by analyzing a flux boundary condition. The GCD framework opens i…

This https://arxiv.org/abs/2307.08298 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Tuple regularity and $k$-ultrahomogeneity for finite groups
For $k, \ell \in \mathbb{N}$, we introduce the concepts of $k$-ultrahomogeneity and $\ell$-tuple regularity for finite groups. Inspired by analogous concepts in graph theory, these form a natural generalization of homogeneity, which was studied by Cherlin and Felgner and Li as well as automorphism transitivity, which was investigated by Zhang. Additionally, these groups have an interesting algorithmic interpretation. We classify the $k$-ultrahomogeneous and $\ell$-tuple regular finite groups fo…

Exhaustive Exploitation of Nature-inspired Computation for Cancer Screening in an Ensemble Manner
Xubin Wang, Yunhe Wang, Zhiqing Ma, Ka-Chun Wong, Xiangtao Li
https://arxiv.org/abs/2404.04547

Exhaustive Exploitation of Nature-inspired Computation for Cancer Screening in an Ensemble Manner
Accurate screening of cancer types is crucial for effective cancer detection and precise treatment selection. However, the association between gene expression profiles and tumors is often limited to a small number of biomarker genes. While computational methods using nature-inspired algorithms have shown promise in selecting predictive genes, existing techniques are limited by inefficient search and poor generalization across diverse datasets. This study presents a framework termed Evolutionary…

A method for quantifying the generalization capabilities of generative models for solving Ising models
Qunlong Ma, Zhi Ma, Ming Gao
https://arxiv.org/abs/2405.03435

A method for quantifying the generalization capabilities of generative models for solving Ising models
For Ising models with complex energy landscapes, whether the ground state can be found by neural networks depends heavily on the Hamming distance between the training datasets and the ground state. Despite the fact that various recently proposed generative models have shown good performance in solving Ising models, there is no adequate discussion on how to quantify their generalization capabilities. Here we design a Hamming distance regularizer in the framework of a class of generative models, …

NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap
Mingrui Li, Jingwei Huang, Lei Sun, Aaron Xuxiang Tian, Tianchen Deng, Hongyu Wang
https://arxiv.org/abs/2405.05702

NGM-SLAM: Gaussian Splatting SLAM with Radiance Field Submap
Gaussian Splatting has garnered widespread attention due to its exceptional performance. Consequently, SLAM systems based on Gaussian Splatting have emerged, leveraging its capabilities for rapid real-time rendering and high-fidelity mapping. However, current Gaussian Splatting SLAM systems usually struggle with large scene representation and lack effective loop closure adjustments and scene generalization capabilities. To address these issues, we introduce NGM-SLAM, the first GS-SLAM system th…

Critical behavior of dirty parafermionic chains
Akshat Pandey, Aditya Cowsik
https://arxiv.org/abs/2404.04324 https://arxiv.org/pdf/2…

Critical behavior of dirty parafermionic chains
A family of $\mathbb Z_n$-symmetric non-Hermitian models of Baxter was shown by Fendley to be exactly solvable via a parafermionic generalization of the Clifford algebra. We study these models with spatially random couplings, and obtain several exact results on thermodynamic singularities as the distributions of couplings are varied. We find that these singularities, independent of $n$, are identical to those in the random transverse-field Ising chain; correspondingly the models host infinite-r…

The impact of data set similarity and diversity on transfer learning success in time series forecasting
Claudia Ehrig, Catherine Cleophas, Germain Forestier
https://arxiv.org/abs/2404.06198

The impact of data set similarity and diversity on transfer learning success in time series forecasting
Models, pre-trained on a similar or diverse source data set, have become pivotal in enhancing the efficiency and accuracy of time series forecasting on target data sets by leveraging transfer learning. While benchmarks validate the performance of model generalization on various target data sets, there is no structured research providing similarity and diversity measures explaining which characteristics of source and target data lead to transfer learning success. Our study pioneers in systematic…

The largest subgraph without a forbidden induced subgraph
Jacob Fox, Rajko Nenadov, Huy Tuan Pham
https://arxiv.org/abs/2405.05902 https://

The largest subgraph without a forbidden induced subgraph
We initiate the systematic study of the following Turán-type question. Suppose $Γ$ is a graph with $n$ vertices such that the edge density between any pair of subsets of vertices of size at least $t$ is at most $1 - c$, for some $t$ and $c > 0$. What is the largest number of edges in a subgraph $G \subseteq Γ$ which does not contain a fixed graph $H$ as an induced subgraph or, more generally, which belongs to a hereditary property $\mathcal{P}$? This provides a common generalization of two r…

This https://arxiv.org/abs/2401.04244 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Spatio-Temporal Turbulence Mitigation: A Translational Perspective
Recovering images distorted by atmospheric turbulence is a challenging inverse problem due to the stochastic nature of turbulence. Although numerous turbulence mitigation (TM) algorithms have been proposed, their efficiency and generalization to real-world dynamic scenarios remain severely limited. Building upon the intuitions of classical TM algorithms, we present the Deep Atmospheric TUrbulence Mitigation network (DATUM). DATUM aims to overcome major challenges when transitioning from classic…

FAIRM: Learning invariant representations for algorithmic fairness and domain generalization with minimax optimality
Sai Li, Linjun Zhang
https://arxiv.org/abs/2404.01608

FAIRM: Learning invariant representations for algorithmic fairness and domain generalization with minimax optimality
Machine learning methods often assume that the test data have the same distribution as the training data. However, this assumption may not hold due to multiple levels of heterogeneity in applications, raising issues in algorithmic fairness and domain generalization. In this work, we address the problem of fair and generalizable machine learning by invariant principles. We propose a training environment-based oracle, FAIRM, which has desirable fairness and domain generalization properties under …

This https://arxiv.org/abs/2211.06617 has been replaced.
link: https://scholar.google.com/scholar?q=a

Empirical Risk Minimization with Relative Entropy Regularization
The empirical risk minimization (ERM) problem with relative entropy regularization (ERM-RER) is investigated under the assumption that the reference measure is a $σ$-finite measure, and not necessarily a probability measure. Under this assumption, which leads to a generalization of the ERM-RER problem allowing a larger degree of flexibility for incorporating prior knowledge, numerous relevant properties are stated. Among these properties, the solution to this problem, if it exists, is shown to…

Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model
Enqiang Xu, Yiming Qiu, Junyang Bai, Ping Zhang, Dadong Miao, Songlin Wang, Guoyu Tang, Lin Liu, Mingming Li
https://arxiv.org/abs/2405.05606

Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model
In large e-commerce platforms, search systems are typically composed of a series of modules, including recall, pre-ranking, and ranking phases. The pre-ranking phase, serving as a lightweight module, is crucial for filtering out the bulk of products in advance for the downstream ranking module. Industrial efforts on optimizing the pre-ranking model have predominantly focused on enhancing ranking consistency, model structure, and generalization towards long-tail items. Beyond these optimizations…

This https://arxiv.org/abs/2108.04376 has been replaced.
link: https://scholar.google.com/scholar?q=a

Counterfactual Effect Generalization: A Combinatorial Definition
The widely used 'Counterfactual' definition of Causal Effects was derived for unbiasedness and accuracy - and not generalizability. We propose a Combinatorial definition for the External Validity (EV) of intervention effects. We first define the concept of an effect observation 'background'. We then formulate conditions for effect generalization based on their sets of (observable and unobservable) backgrounds. This reveals two limits for effect generalization: (1) when effects are observed unde…

On the Gowers trick for classical simple groups
Francesco Fumagalli, Attila Mar\'oti
https://arxiv.org/abs/2404.04967 https://arx…

On the Gowers trick for classical simple groups
If $A$, $B$, $C$ are subsets in a finite simple group of Lie type $G$ at least two of which are normal with $|A||B||C|$ relatively large, then we establish a stronger conclusion than $ABC = G$. This is related to a theorem of Gowers and is a generalization of a theorem of Larsen, Shalev, Tiep and the second author and Pyber.

This https://arxiv.org/abs/2303.04829 has been replaced.
link: https://scholar.google.com/scholar?q=a

Initial value formulation of a quantum damped harmonic oscillator
The in-in formalism and its influence functional generalization are widely used to describe the out-of-equilibrium dynamics of unitary and open quantum systems, respectively. In this paper, we build on these techniques to develop an effective theory of a quantum damped harmonic oscillator and use it to study initial state-dependence, decoherence, and thermalization. We first consider a Gaussian initial state and quadratic influence functional and obtain general equations for the Green's functio…

On Generalized Bihyperbolic Third-order Jacobsthal Polynomials
Gamaliel Cerda-Morales
https://arxiv.org/abs/2404.05738 https://arxiv.…

On Generalized Bihyperbolic Third-order Jacobsthal Polynomials
In this paper, a new generalization of third-order Jacobsthal bihyperbolic polynomials is introduced. Some of the properties of presented polynomials are given. A Vadja formula for the generalized bihyperbolic third-order Jacobsthal polynomials is obtained. This result implies the Catalan, Cassini and d'Ocagne identities. Moreover, generating function and matrix generators for these polynomials are presented.

Super-extremal black holes in the quasitopological electromagnetic field theory
Shahar Hod
https://arxiv.org/abs/2404.03744 https://a…

Super-extremal black holes in the quasitopological electromagnetic field theory
It has recently been proved that a simple generalization of electromagnetism, referred to as quasitopological electromagnetic field theory, is characterized by the presence of dyonic black-hole solutions of the Einstein field equations that, in certain parameter regions, are characterized by four horizons. In the present compact paper we reveal the existence, in this non-linear electrodynamic field theory, of super-extremal black-hole spacetimes that are characterized by the four degenerate fun…

Higher Berry Curvature from the Wave Function I: Schmidt Decomposition and Matrix Product States
Ophelia Evelyn Sommer, Xueda Wen, Ashvin Vishwanath
https://arxiv.org/abs/2405.05316

Higher Berry Curvature from the Wave Function I: Schmidt Decomposition and Matrix Product States
Higher Berry curvature (HBC) is the proposed generalization of Berry curvature to infinitely extended systems. Heuristically HBC captures the flow of local Berry curvature in a system. Here we provide a simple formula for computing the HBC for extended $d = 1$ systems at the level of wave functions using the Schmidt decomposition. We also find a corresponding formula for matrix product states (MPS), and show that for translationally invariant MPS this gives rise to a quantized invariant. We dem…

Generalization of Spivey's recurrence relation
Taekyun Kim, Dae San Kim
https://arxiv.org/abs/2404.02413 https://arxiv.org/pdf/24…

Generalization of Spivey's recurrence relation
In 2008, Spivey found a recurrence relation for the Bell numbers. We consider the probabilistic r-Bell polynomials associated with which are a probabilistic extension of the r-Bell polynomials. Here Y is a random variable whose moment generating function exists in some neighborhood of the origin . The aim of this paper is to generalize the relation for the Bell numbers to that for the probabilistic r-Bell polynomials associated with Y.

This https://arxiv.org/abs/2405.02179 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

Training-Free Deepfake Voice Recognition by Leveraging Large-Scale Pre-Trained Models
Generalization is a main issue for current audio deepfake detectors, which struggle to provide reliable results on out-of-distribution data. Given the speed at which more and more accurate synthesis methods are developed, it is very important to design techniques that work well also on data they were not trained for.In this paper we study the potential of large-scale pre-trained models for audio deepfake detection, with special focus on generalization ability. To this end, the detection problem…

This https://arxiv.org/abs/2402.15852 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
Vision-and-Language Navigation (VLN) stands as a key research problem of Embodied AI, aiming at enabling agents to navigate in unseen environments following linguistic instructions. In this field, generalization is a long-standing challenge, either to out-of-distribution scenes or from Sim to Real. In this paper, we propose NaVid, a video-based large vision language model (VLM), to mitigate such a generalization gap. NaVid makes the first endeavour to showcase the capability of VLMs to achieve …

This https://arxiv.org/abs/2309.03685 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

PyGraft: Configurable Generation of Synthetic Schemas and Knowledge Graphs at Your Fingertips
Knowledge graphs (KGs) have emerged as a prominent data representation and management paradigm. Being usually underpinned by a schema (e.g., an ontology), KGs capture not only factual information but also contextual knowledge. In some tasks, a few KGs established themselves as standard benchmarks. However, recent works outline that relying on a limited collection of datasets is not sufficient to assess the generalization capability of an approach. In some data-sensitive fields such as education…

Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model
Enqiang Xu, Yiming Qiu, Junyang Bai, Ping Zhang, Dadong Miao, Songlin Wang, Guoyu Tang, Lin Liu, Mingming Li
https://arxiv.org/abs/2405.05606

Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model
In large e-commerce platforms, search systems are typically composed of a series of modules, including recall, pre-ranking, and ranking phases. The pre-ranking phase, serving as a lightweight module, is crucial for filtering out the bulk of products in advance for the downstream ranking module. Industrial efforts on optimizing the pre-ranking model have predominantly focused on enhancing ranking consistency, model structure, and generalization towards long-tail items. Beyond these optimizations…

This https://arxiv.org/abs/2404.03221 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Generalized double bracket vector fields
By introducing a metriplectic tensor, we generalize the double bracket vector fields defined on semi-simple Lie algebras to the case of Poisson manifolds endowed with a pseudo-Riemannian metric. We also construct a generalization of the normal metric on an adjoint orbit of a compact semi-simple Lie algebra such that the above vector fields, when restricted to a symplectic leaf, become gradient vector fields. We illustrate the newly introduced objects to a variety of examples and carefully discu…

Generalization of Cycle Decompositions of Even Dimensional Hypercubes on $d$-Dimensional Toruses
Idael Martinez-PerezCarnegie Mellon University
https://arxiv.org/abs/2403.03885

Generalization of Cycle Decompositions of Even Dimensional Hypercubes on $d$-Dimensional Toruses
We consider cycle decompositions of even, $2an$-dimensional hypercubes $Q_{2an},$ where $a \geq 3$ is odd and $n \geq 1.$ Prior work done by Axenovich, Offner, and Tompkins focused on obtaining the existence of cycle decompositions for even-dimensional hypercubes using long cycles of a given form, leaving out cycles of shorter lengths and, in fact, cycles of even longer lengths than those obtained there, such as $C_{7 \cdot 2^{11}}$ in the case of $Q_{14}.$ In this paper, we provide two novel m…

An Information-Theoretic Framework for Out-of-Distribution Generalization
Wenliang Liu, Guanding Yu, Lele Wang, Renjie Liao
https://arxiv.org/abs/2403.19895

An Information-Theoretic Framework for Out-of-Distribution Generalization
We study the Out-of-Distribution (OOD) generalization in machine learning and propose a general framework that provides information-theoretic generalization bounds. Our framework interpolates freely between Integral Probability Metric (IPM) and $f$-divergence, which naturally recovers some known results (including Wasserstein- and KL-bounds), as well as yields new generalization bounds. Moreover, we show that our framework admits an optimal transport interpretation. When evaluated in two concre…

This https://arxiv.org/abs/2402.01810 has been replaced.
link: https://scholar.google.com/scholar?q=a

Parameter uncertainties for imperfect surrogate models in the low-noise regime
Bayesian regression determines model parameters by minimizing the expected loss, an upper bound to the true generalization error. However, the loss ignores misspecification, where models are imperfect. Parameter uncertainties from Bayesian regression are thus significantly underestimated and vanish in the large data limit. This is particularly problematic when building models of low-noise, or near-deterministic, calculations, as the main source of uncertainty is neglected. We analyze the genera…

Simplices osculating rational normal curves
Alessio Caminata, Enrico Carlini, Luca Schaffler
https://arxiv.org/abs/2404.03922 https://

Simplices osculating rational normal curves
A classical result of von Staudt states that if eight planes osculate a twisted cubic curve and we divide them into two groups of four, then the eight vertices of the corresponding tetrahedra lie on a twisted cubic curve. In the current paper, we give an alternative proof of this result using modern tools, and at the same time we prove the analogous result for rational normal curves in any projective space. This higher dimensional generalization was claimed without proof in a paper of H.S. Whit…

This https://arxiv.org/abs/2303.11933 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hept…

Semiclassical approach to form factors in the sinh-Gordon model
Form factors in the sinh-Gordon model are studied semiclassically for small values of the parameter $b\sim\hbar^{1/2}$ in the background of a radial classical solution, which describes a heavy exponential operator placed at the origin. For this purpose we use a generalization of the radial quantization scheme, well known for a massless boson field. We introduce and study new special functions which generalize the Bessel functions and have a nice interpretation in the Tracy-Widom theory of the F…

Generalization of Cycle Decompositions of Even Dimensional Hypercubes on $d$-Dimensional Toruses
Idael Martinez-PerezCarnegie Mellon University
https://arxiv.org/abs/2403.03885

Generalization of Cycle Decompositions of Even Dimensional Hypercubes on $d$-Dimensional Toruses
We consider cycle decompositions of even, $2an$-dimensional hypercubes $Q_{2an},$ where $a \geq 3$ is odd and $n \geq 1.$ Prior work done by Axenovich, Offner, and Tompkins focused on obtaining the existence of cycle decompositions for even-dimensional hypercubes using long cycles of a given form, leaving out cycles of shorter lengths and, in fact, cycles of even longer lengths than those obtained there, such as $C_{7 \cdot 2^{11}}$ in the case of $Q_{14}.$ In this paper, we provide two novel m…

Illustrating the Categorical Landau Paradigm in Lattice Models
Lakshya Bhardwaj, Lea E. Bottini, Sakura Schafer-Nameki, Apoorv Tiwari
https://arxiv.org/abs/2405.05302

Illustrating the Categorical Landau Paradigm in Lattice Models
Recent years have seen the concept of global symmetry extended to non-invertible (or categorical) symmetries, for which composition of symmetry generators is not necessarily invertible. Such non-invertible symmetries lead to a generalization of the standard Landau paradigm. In this work we substantiate this framework by providing a (1+1)d lattice model, whose gapped phases and phase transitions can only be explained by symmetry breaking of non-invertible symmetries.

UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
Juhwan Choi, Yeonghwa Kim, Seunguk Yu, JungMin Yun, YoungBin Kim
https://arxiv.org/abs/2405.01022

UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
Although pre-trained language models have exhibited great flexibility and versatility with prompt-based few-shot learning, they suffer from the extensive parameter size and limited applicability for inference. Recent studies have suggested that PLMs be used as dataset generators and a tiny task-specific model be trained to achieve efficient inference. However, their applicability to various domains is limited because they tend to generate domain-specific datasets. In this work, we propose a nov…

This https://arxiv.org/abs/2401.15868 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_grqc_…

Wormholes inside stars and black holes
We construct models of two exotic objects: (i) a wormhole whose throat is hidden by a stellar object like a neutron star; and (ii) a wormhole inside a black hole. We work within Einstein's gravity coupled to two scalar fields with a specific choice of the scalar field Lagrangian. In general, the model contains ghosts, but they are eliminated using the constraints given by the Lagrange multiplier fields. The constraints are a generalization of the mimetic constraint, where non-dynamical dark mat…

GLHF: General Learned Evolutionary Algorithm Via Hyper Functions
Xiaobin Li, Kai Wu, Yujian Betterest Li, Xiaoyu Zhang, Handing Wang, Jing Liu
https://arxiv.org/abs/2405.03728

GLHF: General Learned Evolutionary Algorithm Via Hyper Functions
Pretrained Optimization Models (POMs) leverage knowledge gained from optimizing various tasks, providing efficient solutions for new optimization challenges through direct usage or fine-tuning. Despite the inefficiencies and limited generalization abilities observed in current POMs, our proposed model, the general pre-trained optimization model (GPOM), addresses these shortcomings. GPOM constructs a population-based pretrained Black-Box Optimization (BBO) model tailored for continuous optimizat…

This https://arxiv.org/abs/2205.07739 has been replaced.
link: https://scholar.google.com/scholar?q=a

The Role of Pseudo-labels in Self-training Linear Classifiers on High-dimensional Gaussian Mixture Data
Self-training (ST) is a simple yet effective semi-supervised learning method. However, why and how ST improves generalization performance by using potentially erroneous pseudo-labels is still not well understood. To deepen the understanding of ST, we derive and analyze a sharp characterization of the behavior of iterative ST when training a linear classifier by minimizing the ridge-regularized convex loss on binary Gaussian mixtures, in the asymptotic limit where input dimension and data size d…

This https://arxiv.org/abs/2402.18699 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Articulated Object Manipulation with Coarse-to-fine Affordance for Mitigating the Effect of Point Cloud Noise
3D articulated objects are inherently challenging for manipulation due to the varied geometries and intricate functionalities associated with articulated objects.Point-level affordance, which predicts the per-point actionable score and thus proposes the best point to interact with, has demonstrated excellent performance and generalization capabilities in articulated object manipulation. However, a significant challenge remains: while previous works use perfect point cloud generated in simulatio…

Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning
Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Haoze Sun, Xueyi Zou, Zhensong Zhang, Youliang Yan, Lei Zhu
https://arxiv.org/abs/2403.02601

Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning
For image super-resolution (SR), bridging the gap between the performance on synthetic datasets and real-world degradation scenarios remains a challenge. This work introduces a novel "Low-Res Leads the Way" (LWay) training framework, merging Supervised Pre-training with Self-supervised Learning to enhance the adaptability of SR models to real-world images. Our approach utilizes a low-resolution (LR) reconstruction network to extract degradation embeddings from LR images, merging them with super…

This https://arxiv.org/abs/2307.10651 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Distributional Regression for Data Analysis
Flexible modeling of the entire distribution as a function of covariates is an important generalization of mean-based regression that has seen growing interest over the past decades in both the statistics and machine learning literature. This review outlines selected state-of-the-art statistical approaches to distributional regression, complemented with alternatives from machine learning. Topics covered include the similarities and differences between these approaches, extensions, properties an…

This https://arxiv.org/abs/2212.11243 has been replaced.
link: https://scholar.google.com/scholar?q=a

Color-Dressed Generalized Biadjoint Scalar Amplitudes: Local Planarity
The biadjoint scalar theory has cubic interactions and fields transforming in the biadjoint representation of ${\rm SU}(N)\times {\rm SU}\big({\tilde N}\big)$. Amplitudes are "color" decomposed in terms of partial amplitudes computed using Feynman diagrams which are simultaneously planar with respect to two orderings. In 2019, a generalization of biadjoint scalar amplitudes based on generalized Feynman diagrams (GFDs) was introduced. GFDs are collections of Feynman diagrams derived by incorpora…

Higher Berry Phase from Projected Entangled Pair States in (2 1) dimensions
Shuhei Ohyama, Shinsei Ryu
https://arxiv.org/abs/2405.05325 https://

Higher Berry Phase from Projected Entangled Pair States in (2+1) dimensions
We consider families of invertible many-body quantum states in $d$ spatial dimensions that are parameterized over some parameter space $X$. The space of such families is expected to have topologically distinct sectors classified by the cohomology group $\mathrm{H}^{d+2}(X;\mathbb{Z})$. These topological sectors are distinguished by a topological invariant built from a generalization of the Berry phase, called the higher Berry phase. In the previous work, we introduced a generalized inner produc…

This https://arxiv.org/abs/2402.18699 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Articulated Object Manipulation with Coarse-to-fine Affordance for Mitigating the Effect of Point Cloud Noise
3D articulated objects are inherently challenging for manipulation due to the varied geometries and intricate functionalities associated with articulated objects.Point-level affordance, which predicts the per-point actionable score and thus proposes the best point to interact with, has demonstrated excellent performance and generalization capabilities in articulated object manipulation. However, a significant challenge remains: while previous works use perfect point cloud generated in simulatio…

This https://arxiv.org/abs/2402.14494 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task
In a realistic dialogue system, the input information from users is often subject to various types of input perturbations, which affects the slot-filling task. Although rule-based data augmentation methods have achieved satisfactory results, they fail to exhibit the desired generalization when faced with unknown noise disturbances. In this study, we address the challenges posed by input perturbations in slot filling by proposing Noise-BERT, a unified Perturbation-Robust Framework with Noise Ali…

Higher Berry Curvature from the Wave function II: Locally Parameterized States Beyond One Dimension
Ophelia Evelyn Sommer, Ashvin Vishwanath, Xueda Wen
https://arxiv.org/abs/2405.05323

Higher Berry Curvature from the Wave function II: Locally Parameterized States Beyond One Dimension
We propose a systematic wave function based approach to construct topological invariants for families of lattice systems that are short-range entangled using local parameter spaces. This construction is particularly suitable when given a family of tensor networks that can be viewed as the ground states of $d$ dimensional lattice systems, for which we construct the closed $(d+2)$-form higher Berry curvature, which is a generalization of the well known 2-form Berry curvature. Such $(d+2)$-form hi…

Macdonald characters from a new formula for Macdonald polynomials
Houcine Ben Dali, Michele D'Adderio
https://arxiv.org/abs/2404.03904 https://<…

Macdonald characters from a new formula for Macdonald polynomials
We introduce a new operator $Γ$ on symmetric functions, which enables us to obtain a creation formula for Macdonald polynomials. This formula provides a connection between the theory of Macdonald operators initiated by Bergeron, Garsia, Haiman and Tesler, and shifted Macdonald polynomials introduced by Knop, Lassalle, Okounkov and Sahi. We use this formula to introduce a two-parameter generalization of Jack characters, which we call Macdonald characters. Finally, we provide a change of varia…

Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation
Shanshan Feng, Haoming Lyu, Caishun Chen, Yew-Soon Ong
https://arxiv.org/abs/2404.01855

Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation
Next Point-of-interest (POI) recommendation provides valuable suggestions for users to explore their surrounding environment. Existing studies rely on building recommendation models from large-scale users' check-in data, which is task-specific and needs extensive computational resources. Recently, the pretrained large language models (LLMs) have achieved significant advancements in various NLP tasks and have also been investigated for recommendation scenarios. However, the generalization abilit…

This https://arxiv.org/abs/2405.01022 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
Although pre-trained language models have exhibited great flexibility and versatility with prompt-based few-shot learning, they suffer from the extensive parameter size and limited applicability for inference. Recent studies have suggested that PLMs be used as dataset generators and a tiny task-specific model be trained to achieve efficient inference. However, their applicability to various domains is limited because they tend to generate domain-specific datasets. In this work, we propose a nov…

This https://arxiv.org/abs/2309.13285 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning
End-to-end deep reinforcement learning (DRL) for quadrotor control promises many benefits -- easy deployment, task generalization and real-time execution capability. Prior end-to-end DRL-based methods have showcased the ability to deploy learned controllers onto single quadrotors or quadrotor teams maneuvering in simple, obstacle-free environments. However, the addition of obstacles increases the number of possible interactions exponentially, thereby increasing the difficulty of training RL pol…

Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation
Shanshan Feng, Haoming Lyu, Caishun Chen, Yew-Soon Ong
https://arxiv.org/abs/2404.01855

Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation
Next Point-of-interest (POI) recommendation provides valuable suggestions for users to explore their surrounding environment. Existing studies rely on building recommendation models from large-scale users' check-in data, which is task-specific and needs extensive computational resources. Recently, the pretrained large language models (LLMs) have achieved significant advancements in various NLP tasks and have also been investigated for recommendation scenarios. However, the generalization abilit…