Tootfinder

Delighted to see these two new papers come out in Nature (they've been on bioRxiv for a while).
How does Pavlov's dog learn that the bell predicts the food? One answer is that the bell appears ``close'' in time to the food and that enables learning. We're certain that dopamine has something to do with learning these kinds of associations. But the definition of ``close'' in time is actually really difficult to pin down. You can get associations over prett…

Multi-timescale reinforcement learning in the brain - Nature
Individual dopaminergic neurons encode future rewards over distinct temporal horizons.

This https://arxiv.org/abs/2503.10503 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Sample Compression for Continual Learning
Continual learning algorithms aim to learn from a sequence of tasks, making the training distribution non-stationary. The majority of existing continual learning approaches in the literature rely on heuristics and do not provide learning guarantees. In this paper, we present a new method called Continual Pick-to-Learn (CoP2L), which is able to retain the most representative samples for each task in an efficient way. CoP2L combines the Pick-to-Learn algorithm (rooted in the sample compression th…

Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models
Armin Keki\'c, Sergio Hernan Garrido Mejia, Bernhard Sch\"olkopf
https://arxiv.org/abs/2506.04945

Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models
Estimating causal effects of joint interventions on multiple variables is crucial in many domains, but obtaining data from such simultaneous interventions can be challenging. Our study explores how to learn joint interventional effects using only observational data and single-variable interventions. We present an identifiability result for this problem, showing that for a class of nonlinear additive outcome mechanisms, joint effects can be inferred without access to joint interventional data. W…

This https://arxiv.org/abs/2406.18370 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Learning pure quantum states (almost) without regret
We initiate the study of sample-optimal quantum state tomography with minimal disturbance to the samples. Can we efficiently learn a precise description of a quantum state through sequential measurements of samples while at the same time making sure that the post-measurement state of the samples is only minimally perturbed? Defining regret as the cumulative disturbance of all samples, the challenge is to find a balance between the most informative sequence of measurements on the one hand and me…

This https://arxiv.org/abs/2504.17959 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

CIVIL: Causal and Intuitive Visual Imitation Learning
Today's robots learn new tasks by imitating human examples. However, this standard approach to visual imitation learning is fundamentally limited: the robot observes what the human does, but not why the human chooses those behaviors. Without understanding the features that factor into the human's decisions, robot learners often misinterpret the data and fail to perform the task when the environment changes. We therefore propose a shift in perspective: instead of asking human teachers just to sh…

This https://arxiv.org/abs/2503.18938 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

AdaWorld: Learning Adaptable World Models with Latent Actions
World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training, making it challenging to adapt to novel environments with heterogeneous actions through limited interactions. This limitation can hinder their applicability across broader domains. To overcome this limitation, we propose AdaWorld, an innovative world model learni…

Learning to crawl: benefits and limits of centralized vs distributed control
Luca Gagliardi, Agnese Seminara
https://arxiv.org/abs/2506.02766 https://

Learning to crawl: benefits and limits of centralized vs distributed control
We present a model of a crawler consisting of several suckers distributed along a straight line and connected by springs. Both proprioception and control are binary: the system responds to the elongation vs compression of its springs and the suckers can either adhere or remain idle. A central pattern generator delivers a traveling wave of compression, and the crawler is tasked to learn how to control adhesion to effectively ride the wave in order to crawl. We ask what are the benefits and limit…

This https://arxiv.org/abs/2309.07443 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Learning Tube-Certified Control using Robust Contraction Metrics
Control design for general nonlinear robotic systems with guaranteed stability and/or safety in the presence of model uncertainties is a challenging problem. Recent efforts attempt to learn a controller and a certificate (e.g., a Lyapunov function or a contraction metric) jointly using neural networks (NNs), in which model uncertainties are generally ignored during the learning process. In this paper, for nonlinear systems subject to bounded disturbances, we present a framework for jointly lear…

This https://arxiv.org/abs/2503.09492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Learning Cascade Ranking as One Network
Cascade Ranking is a prevalent architecture in large-scale top-k selection systems like recommendation and advertising platforms. Traditional training methods focus on single-stage optimization, neglecting interactions between stages. Recent advances have introduced interaction-aware training paradigms, but still struggle to 1) align training objectives with the goal of the entire cascade ranking (i.e., end-to-end recall of ground-truth items) and 2) learn effective collaboration patterns for d…

This https://arxiv.org/abs/2303.17475 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning distributed representations with efficient SoftMax normalization
Learning distributed representations, or embeddings, that encode the relational similarity patterns among objects is a relevant task in machine learning. A popular method to learn the embedding matrices $X, Y$ is optimizing a loss function of the term ${\rm SoftMax}(XY^T)$. The complexity required to calculate this term, however, runs quadratically with the problem size, making it a computationally heavy solution. In this article, we propose a linear-time heuristic approximation to compute the …

Modern search demands scalable personalisation. Join Piotr Kobziakowski
at this year's Berlin Buzzwords to discover how Vespa's multi-stage ranking and tensor framework can be used for hybrid queries, multimodal retrieval, and real-time machine learning. Learn how to deploy low-latency, high-relevance search systems at petabyte scale.
Learn more:

Vespa.ai’s Personalized Search: Advanced Ranking & Tensor framework
Today’s applications require search engines to unify text, vectors, and business logic with millisecond latency at petabyte scale. It’s not easy to balance speed, relevance, and personalization for a large user population and a billion scale item base. Vespa.ai, the open-source engine powering Yahoo, Perplexity, Qwant, Vinted, Spotify addresses this through multi-stage ranking with close to data tensor operations and easy to understand custom functions. Vespa’s phased architecture enables…

The first #DevOpsDaysAustin keynote is @… talking about failing to learn vs. learning to fail.

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
Hao Li, Qi Lv, Rui Shao, Xiang Deng, Yinchuan Li, Jianye Hao, Liqiang Nie
https://arxiv.org/abs/2506.03863

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models, e.g., VQ-VAE, to learn skill abstractions through learned vectors (codebooks), while they suffer from codebook collapse and modeling the causal relationship between learned skills. To address these limitations, we present \textbf{S}kill \textbf{T}raining with \textbf{A}ugmented \textbf{R}otation (\textbf{STAR}), a f…

AI doesn’t learn like we do. GoPro'd toddlers see mostly knees—but they can ID a dog after a few glimpses, while LLMs need billions of examples. Neuroscience suggests AI intelligence is gathered very differently than ours https://www.linkedin.com/p…

Deep learning of thermodynamic laws from microscopic dynamics
Hiroto Kuroyanagi, Tatsuro Yuge
https://arxiv.org/abs/2506.01506 https://

Deep learning of thermodynamic laws from microscopic dynamics
We numerically show that a deep neural network (DNN) can learn macroscopic thermodynamic laws purely from microscopic data. Using molecular dynamics simulations, we generate the data of snapshot images of gas particles undergoing adiabatic processes. We train a DNN to determine the temporal order of input image pairs. We observe that the trained network induces an order relation between states consistent with adiabatic accessibility, satisfying the axioms of thermodynamics. Furthermore, the int…

This https://arxiv.org/abs/2505.19946 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Inverse Q-Learning Done Right: Offline Imitation Learning in $Q^π$-Realizable MDPs
We study the problem of offline imitation learning in Markov decision processes (MDPs), where the goal is to learn a well-performing policy given a dataset of state-action pairs generated by an expert policy. Complementing a recent line of work on this topic that assumes the expert belongs to a tractable class of known policies, we approach this problem from a new angle and leverage a different type of structural assumption about the environment. Specifically, for the class of linear $Q^π$-rea…

Learning to Charge More: A Theoretical Study of Collusion by Q-Learning Agents
Cristian Chica, Yinglong Guo, Gilad Lerman
https://arxiv.org/abs/2505.22909 …

Learning to Charge More: A Theoretical Study of Collusion by Q-Learning Agents
There is growing experimental evidence that $Q$-learning agents may learn to charge supracompetitive prices. We provide the first theoretical explanation for this behavior in infinite repeated games. Firms update their pricing policies based solely on observed profits, without computing equilibrium strategies. We show that when the game admits both a one-stage Nash equilibrium price and a collusive-enabling price, and when the $Q$-function satisfies certain inequalities at the end of experiment…

What's going on with this #ICLR paper?
The metareview says that the authors provided a sound rebuttal and update to the paper, but neither are available (rebuttals are shown on other papers).
https://openreview.…

GLoRa: A Benchmark to Evaluate the Ability to Learn Long-Range...
Learning on graphs is one of the most active research topics in machine learning (ML). Among the key challenges in this field, effectively learning long-range dependencies in graphs has been...

Comparative analysis of computational approaches for predicting Transthyretin transcription activators and human dopamine D1 receptor antagonists
Mariya L. Ivanova, Nicola Russo, Konstantin Nikolic
https://arxiv.org/abs/2506.01137

Comparative analysis of computational approaches for predicting Transthyretin transcription activators and human dopamine D1 receptor antagonists
The study expands the application of scikit-learn-based machine learning (ML) to the prediction of small biomolecule functionalities based on Carbon 13 isotope (13C) NMR spectroscopy data derived from Simplified Molecular Input Line Entry System (SMILES) notations. The methodology previously demonstrated by predicting dopamine D1 receptor antagonists was upgraded with addition of new molecular features derived from the PubChem database. The enhanced ML model obtained 75.8% Accuracy, 84.2% Preci…

This https://arxiv.org/abs/2308.13140 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Learn With Imagination: Safe Set Guided State-wise Constrained Policy Optimization
Deep reinforcement learning (RL) excels in various control tasks, yet the absence of safety guarantees hampers its real-world applicability. In particular, explorations during learning usually results in safety violations, while the RL agent learns from those mistakes. On the other hand, safe control techniques ensure persistent safety satisfaction but demand strong priors on system dynamics, which is usually hard to obtain in practice. To address these problems, we present Safe Set Guided Stat…

Next stop in our NLP timeline is 2013, the introduction of low dimensional dense word vectors - so-called "word embeddings" - based on distributed semantics, as e.g. word2vec by Mikolov et al. from Google, which enabled representation learning on text.
T. Mikolov et al. (2013). Efficient Estimation of Word Representations in Vector Space.
…

Efficient Estimation of Word Representations in Vector Space
We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a word similarity task, and the results are compared to the previously best performing techniques based on different types of neural networks. We observe large improvements in accuracy at much lower computational cost, i.e. it takes less than a day to learn high quality word vectors from a 1.6 billion words data set. Fur…

A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
Jakub Martinka, Lina Zhang, Yi-Fan Hou, Miko{\l}aj Martyka, Ji\v{r}\'i Pittner, Mario Barbatti, Pavlo O. Dral
https://arxiv.org/abs/2505.23344

A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
Nonadiabatic couplings (NACs) play a crucial role in modeling photochemical and photophysical processes with methods such as the widely used fewest-switches surface hopping (FSSH). There is therefore a strong incentive to machine learn NACs for accelerating simulations. However, this is challenging due to NACs' vectorial, double-valued character and the singularity near a conical intersection seam. For the first time, we design NAC-specific descriptors based on our domain expertise and show tha…

This https://arxiv.org/abs/2401.17909 has been replaced.
link: https://scholar.google.com/scholar?q=a

Regularizing Fairness in Optimal Policy Learning with Distributional Targets
A decision maker typically (i) incorporates training data to learn about the relative effectiveness of treatments, and (ii) chooses an implementation mechanism that implies an ``optimal'' predicted outcome distribution according to some target functional. Nevertheless, a fairness-aware decision maker may not be satisfied achieving said optimality at the cost of being ``unfair" against a subgroup of the population, in the sense that the outcome distribution in that subgroup deviates too strongly…

This https://arxiv.org/abs/2409.03685 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

View-Invariant Policy Learning via Zero-Shot Novel View Synthesis
Large-scale visuomotor policy learning is a promising approach toward developing generalizable manipulation systems. Yet, policies that can be deployed on diverse embodiments, environments, and observational modalities remain elusive. In this work, we investigate how knowledge from large-scale visual data of the world may be used to address one axis of variation for generalizable manipulation: observational viewpoint. Specifically, we study single-image novel view synthesis models, which learn …

This https://arxiv.org/abs/2412.17629 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Learn from Global Correlations: Enhancing Evolutionary Algorithm via Spectral GNN
Evolutionary algorithms (EAs) simulate natural selection but have two main limitations: (1) they rarely update individuals based on global correlations, limiting comprehensive learning; (2) they struggle with balancing exploration and exploitation, where excessive exploitation causes premature convergence, and excessive exploration slows down the search. Moreover, EAs often depend on manual parameter settings, which can disrupt the exploration-exploitation balance.To address these issues, we pr…

At Berlin Buzzwords 2025, join Dhrubo Saha to discover how OpenSearch pipelines are integrating ML inference processors for powerful multi-modal search. Learn to search directly within images, audio, and text – locally on your own hardware!
Learn more: https://

This https://arxiv.org/abs/2503.09492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Learning Cascade Ranking as One Network
Cascade Ranking is a prevalent architecture in large-scale top-k selection systems like recommendation and advertising platforms. Traditional training methods focus on single-stage optimization, neglecting interactions between stages. Recent advances have introduced interaction-aware training paradigms, but still struggle to 1) align training objectives with the goal of the entire cascade ranking (i.e., end-to-end recall of ground-truth items) and 2) learn effective collaboration patterns for d…

This https://arxiv.org/abs/2412.17629 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Learn from Global Correlations: Enhancing Evolutionary Algorithm via Spectral GNN
Evolutionary algorithms (EAs) simulate natural selection but have two main limitations: (1) they rarely update individuals based on global correlations, limiting comprehensive learning; (2) they struggle with balancing exploration and exploitation, where excessive exploitation causes premature convergence, and excessive exploration slows down the search. Moreover, EAs often depend on manual parameter settings, which can disrupt the exploration-exploitation balance.To address these issues, we pr…