Tootfinder

One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
Miko{\l}aj Janusz, Tomasz Wojnar, Yawei Li, Luca Benini, Kamil Adamczewski
https://arxiv.org/abs/2508.13836

One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
Pruning is a core technique for compressing neural networks to improve computational efficiency. This process is typically approached in two ways: one-shot pruning, which involves a single pass of training and pruning, and iterative pruning, where pruning is performed over multiple cycles for potentially finer network refinement. Although iterative pruning has historically seen broader adoption, this preference is often assumed rather than rigorously tested. Our study presents one of the first …

Iterated integrals on the Legendre family of elliptic curves
Eisuke Otsuka
https://arxiv.org/abs/2507.13790 https://arxiv.org/pdf/250…

Iterated integrals on the Legendre family of elliptic curves
K.T. Chen showed that iterated integrals give comparison isomorphisms between the cohomologies of bar complexes and fundamental group rings. This led to the development of an algebraic-geometric approach to studying periods given by iterated integrals. In this paper we consider an analogue of this comparison isomorphism theorem for iterated integrals on the Legendre family.

Reference-Free Iterative Learning Model Predictive Control with Neural Certificates
Wataru Hashimoto, Kazumune Hashimoto, Masako Kishida, Shigemasa Takai
https://arxiv.org/abs/2507.14025

Reference-Free Iterative Learning Model Predictive Control with Neural Certificates
In this paper, we propose a novel reference-free iterative learning model predictive control (MPC). In the proposed method, a certificate function based on the concept of Control Lyapunov Barrier Function (CLBF) is learned using data collected from past control executions and used to define the terminal set and cost in the MPC optimization problem at the current iteration. This scheme enables the progressive refinement of the MPC's terminal components over successive iterations. Unlike existing…

from my link log —
Golang's weird little iterators.
https://mcyoung.xyz/2024/12/16/rangefuncs/#fnref:tooling
saved 2024-12-17

Go's Weird Little Iterators · mcyoung

On spurious fixed points in iterative maximum likelihood reconstruction for quantum tomography
Florian Oberender
https://arxiv.org/abs/2508.14549 https://a…

On spurious fixed points in iterative maximum likelihood reconstruction for quantum tomography
Maximum likelihood iteration is one of the most commonly used reconstruction algorithms in quantum tomography. The main appeal of the method is that it is easy to implement and that it converges reliably to a physically meaningful density matrix in practice. Contradicting these practical observations, we will show that convergence to a true solution is not guaranteed in general by constructing examples for spurious fixed points. To deal with this newly found problem, we then provide a criterion…

Iteratively Learning Muscle Memory for Legged Robots to Master Adaptive and High Precision Locomotion
Jing Cheng, Yasser G. Alqaham, Zhenyu Gan, Amit K. Sanyal
https://arxiv.org/abs/2507.13662

Iteratively Learning Muscle Memory for Legged Robots to Master Adaptive and High Precision Locomotion
This paper presents a scalable and adaptive control framework for legged robots that integrates Iterative Learning Control (ILC) with a biologically inspired torque library (TL), analogous to muscle memory. The proposed method addresses key challenges in robotic locomotion, including accurate trajectory tracking under unmodeled dynamics and external disturbances. By leveraging the repetitive nature of periodic gaits and extending ILC to nonperiodic tasks, the framework enhances accuracy and gen…

Last-Iterate Complexity of SGD for Convex and Smooth Stochastic Problems
Guillaume Garrigos, Daniel Cortild, Lucas Ketels, Juan Peypouquet
https://arxiv.org/abs/2507.14122

Last-Iterate Complexity of SGD for Convex and Smooth Stochastic Problems
Most results on Stochastic Gradient Descent (SGD) in the convex and smooth setting are presented under the form of bounds on the ergodic function value gap. It is an open question whether bounds can be derived directly on the last iterate of SGD in this context. Recent advances suggest that it should be possible. For instance, it can be achieved by making the additional, yet unverifiable, assumption that the variance of the stochastic gradients is uniformly bounded. In this paper, we show that …

Learning Iterated Function Systems from Time Series of Partial Observations
Emilia Gibson, Jeroen S. W. Lamb
https://arxiv.org/abs/2508.13794 https://arxiv…

Learning Iterated Function Systems from Time Series of Partial Observations
We develop a methodology to learn finitely generated random iterated function systems from time-series of partial observations using delay embeddings. We obtain a minimal model representation for the observed dynamics, using a hidden variable representation, that is diffeomorphic to the original system.

Iterative Youla-Kucera Loop Shaping For Precision Motion Control
Xiaohai Hu, Jason Laks, Guoxiao Guo, Xu Chen
https://arxiv.org/abs/2508.14309 https://arxi…

Iterative Youla-Kucera Loop Shaping For Precision Motion Control
This paper presents a numerically robust approach to multi-band disturbance rejection using an iterative Youla-Kucera parameterization technique. The proposed method offers precise control over shaping the frequency response of a feedback loop while maintaining numerical stability through a systematic design process. By implementing an iterative approach, we overcome a critical numerical issue in rejecting vibrations with multiple frequency bands. Meanwhile, our proposed modification of the all…

Revisiting Diffusion Q-Learning: From Iterative Denoising to One-Step Action Generation
Thanh Nguyen, Chang D. Yoo
https://arxiv.org/abs/2508.13904 https://

Revisiting Diffusion Q-Learning: From Iterative Denoising to One-Step Action Generation
The generative power of diffusion models (DMs) has recently enabled high-performing decision-making algorithms in offline reinforcement learning (RL), achieving state-of-the-art results across standard benchmarks. Among them, Diffusion Q-Learning (DQL) stands out as a leading method for its consistently strong performance. Nevertheless, DQL remains limited in practice due to its reliance on multi-step denoising for action generation during both training and inference. Although one-step denoisin…