English
Related papers

Related papers: Lower and Upper Bounds on CSL Parameters from Late…

200 papers

Collaborative learning through latent shared feature representations enables heterogeneous clients to train personalized models with improved performance and reduced sample complexity. Despite empirical success and extensive study, the…

Machine Learning · Computer Science 2025-11-25 Xiaochun Niu , Lili Su , Jiaming Xu , Pengkun Yang

This paper presents InterMPL, a semi-supervised learning method of end-to-end automatic speech recognition (ASR) that performs pseudo-labeling (PL) with intermediate supervision. Momentum PL (MPL) trains a connectionist temporal…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-20 Yosuke Higuchi , Tetsuji Ogawa , Tetsunori Kobayashi , Shinji Watanabe

We present a local minimax lower bound on the excess cost of designing a linear-quadratic controller from offline data. The bound is valid for any offline exploration policy that consists of a stabilizing controller and an energy bounded…

Systems and Control · Electrical Eng. & Systems 2023-03-29 Bruce D. Lee , Ingvar Ziemann , Anastasios Tsiamis , Henrik Sandberg , Nikolai Matni

Stochastic gradient descent (SGD) has emerged as the quintessential method in a data scientist's toolbox. Using SGD for high-stakes applications requires, however, careful quantification of the associated uncertainty. Towards that end, in…

Statistics Theory · Mathematics 2025-10-24 Bhavya Agrawalla , Krishnakumar Balasubramanian , Promit Ghosal

Overheating anomaly detection is essential for the quality and reliability of parts produced by laser powder bed fusion (LPBF) additive manufacturing (AM). In this research, we focus on the detection of overheating anomalies using…

Machine Learning · Computer Science 2024-03-22 Nazmul Hasan , Apurba Kumar Saha , Andrew Wessman , Mohammed Shafae

Large Language Models (LLMs), such as GPT models, are increasingly used in software engineering for various tasks, such as code generation, requirements management, and debugging. While automating these tasks has garnered significant…

Software Engineering · Computer Science 2024-08-21 Chetan Arora , Ahnaf Ibn Sayeed , Sherlock Licorish , Fanyu Wang , Christoph Treude

Single-image super-resolution (SISR) typically focuses on restoring various degraded low-resolution (LR) images to a single high-resolution (HR) image. However, during SISR tasks, it is often challenging for models to simultaneously…

Image and Video Processing · Electrical Eng. & Systems 2023-11-10 Xin Wang , Jing-Ke Yan , Jing-Ye Cai , Jian-Hua Deng , Qin Qin , Yao Cheng

We consider minimum variance estimation within the sparse linear Gaussian model (SLGM). A sparse vector is to be estimated from a linearly transformed version embedded in Gaussian noise. Our analysis is based on the theory of reproducing…

Information Theory · Computer Science 2013-04-16 Alexander Jung , Sebastian Schmutzhard , Franz Hlawatsch , Zvika Ben-Haim , Yonina C. Eldar

Recent theoretical works have characterized the dynamics of wide shallow neural networks trained via gradient descent in an asymptotic mean-field limit when the width tends towards infinity. At initialization, the random sampling of the…

Probability · Mathematics 2022-03-29 Zhengdao Chen , Grant M. Rotskoff , Joan Bruna , Eric Vanden-Eijnden

In this work, we consider the dynamics of the self-induced collapse of the tachyon wave function in inflationary scenarios. We analyze the modifications on the power spectrum by considering the $\beta$-exponential potential, whose…

Cosmology and Nongalactic Astrophysics · Physics 2025-11-24 F. A. Brito , Julio C. M. Rocha , A. S. Lemos , A. S. Pereira

Restricted Boltzmann Machines (RBM) have attracted a lot of attention of late, as one the principle building blocks of deep networks. Training RBMs remains problematic however, because of the intractibility of their partition function. The…

Machine Learning · Statistics 2010-12-17 Guillaume Desjardins , Aaron Courville , Yoshua Bengio

Reduced-rank approach has been used for decades in robust linear estimation of both deterministic and random vector of parameters in linear model y=Hx+\sqrt{epsilon}n. In practical settings, estimation is frequently performed under…

Optimization and Control · Mathematics 2024-08-05 Tomasz Piotrowski , Isao Yamada

We propose Bayesian optimal sequential prediction as a new principle for understanding in-context learning (ICL). Unlike interpretations framing Transformers as performing implicit gradient descent, we formalize ICL as meta-learning over…

Machine Learning · Computer Science 2026-02-23 Di Zhang , Jiaqi Xing

The lensing power spectrum from cosmic microwave background (CMB) temperature maps will be measured with unprecedented precision with upcoming experiments, including upgrades to ACT and SPT. Achieving significant improvements in…

Cosmology and Nongalactic Astrophysics · Physics 2015-06-17 A. van Engelen , S. Bhattacharya , N. Sehgal , G. P. Holder , O. Zahn , D. Nagai

For the problem of high-dimensional sparse linear regression, it is known that an $\ell_0$-based estimator can achieve a $1/n$ "fast" rate on the prediction error without any conditions on the design matrix, whereas in absence of…

Statistics Theory · Mathematics 2015-12-01 Yuchen Zhang , Martin J. Wainwright , Michael I. Jordan

This paper deals with subspace estimation in the small sample size regime, where the number of samples is comparable in magnitude with the observation dimension. The traditional estimators, mostly based on the sample correlation matrix, are…

Methodology · Statistics 2015-06-19 Pascal Vallet , Xavier Mestre , Philippe Loubaton

We study deep state-space models (Deep SSMs) that contain linear quadratic-output (LQO) systems as internal blocks and present a compression method with a provable output error guarantee. We first derive an upper bound on the output error…

Systems and Control · Electrical Eng. & Systems 2026-05-27 Hiroki Sakamoto , Kazuhiro Sato

Large Language models (LLMs) have achieved encouraging results in tabular data generation. However, existing approaches require fine-tuning, which is computationally expensive. This paper explores an alternative: prompting a fixed LLM with…

Machine Learning · Computer Science 2025-02-25 Liancheng Fang , Aiwei Liu , Hengrui Zhang , Henry Peng Zou , Weizhi Zhang , Philip S. Yu

Stochastic convex optimization over an $\ell_1$-bounded domain is ubiquitous in machine learning applications such as LASSO but remains poorly understood when learning with differential privacy. We show that, up to logarithmic factors the…

Machine Learning · Computer Science 2021-03-03 Hilal Asi , Vitaly Feldman , Tomer Koren , Kunal Talwar

The talk presented at ICMP 97 focused on the scaling limits of critical percolation models, and some other systems whose salient features can be described by collections of random lines. In the scaling limit we keep track of features seen…

Mathematical Physics · Physics 2007-05-23 Michael Aizenman