English
Related papers

Related papers: Leveraging Sparsity for Sample-Efficient Preferenc…

200 papers

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…

Machine Learning · Computer Science 2025-03-05 Kexin Huang , Junkang Wu , Ziqian Chen , Xue Wang , Jinyang Gao , Bolin Ding , Jiancan Wu , Xiangnan He , Xiang Wang

Motivated by applications of large embedding models, we study differentially private (DP) optimization problems under sparsity of individual gradients. We start with new near-optimal bounds for the classic mean estimation problem but with…

Machine Learning · Computer Science 2024-11-01 Badih Ghazi , Cristóbal Guzmán , Pritish Kamath , Ravi Kumar , Pasin Manurangsi

Principal component analysis (PCA) is one of the most commonly used statistical procedures with a wide range of applications. This paper considers both minimax and adaptive estimation of the principal subspace in the high dimensional…

Statistics Theory · Mathematics 2014-01-08 T. Tony Cai , Zongming Ma , Yihong Wu

Sparse recovery is among the most well-studied problems in learning theory and high-dimensional statistics. In this work, we investigate the statistical and computational landscapes of sparse recovery with $\ell_\infty$ error guarantees.…

Statistics Theory · Mathematics 2026-02-19 Ziyun Chen , Jerry Li , Kevin Tian , Yusong Zhu

Multi-task learning leverages structural similarities between multiple tasks to learn despite very few samples. Motivated by the recent success of neural networks applied to data-scarce tasks, we consider a linear low-dimensional shared…

Machine Learning · Statistics 2022-06-13 Etienne Boursier , Mikhail Konobeev , Nicolas Flammarion

Robust mean estimation is one of the most important problems in statistics: given a set of samples in $\mathbb{R}^d$ where an $\alpha$ fraction are drawn from some distribution $D$ and the rest are adversarially corrupted, we aim to…

Machine Learning · Computer Science 2022-12-07 Shiwei Zeng , Jie Shen

In unsupervised learning, an unbiased uniform sampling strategy is typically used, in order that the learned features faithfully encode the statistical structure of the training data. In this work, we explore whether active example…

Machine Learning · Computer Science 2015-04-01 Tomoki Tsuchida , Garrison W. Cottrell

We present a new approach for efficient exploration which leverages a low-dimensional encoding of the environment learned with a combination of model-based and model-free objectives. Our approach uses intrinsic rewards that are based on the…

Machine Learning · Computer Science 2022-04-18 Ruo Yu Tao , Vincent François-Lavet , Joelle Pineau

This paper addresses the problem of sequential submodular maximization: selecting and ranking items in a sequence to optimize some composite submodular function. In contrast to most of the previous works, which assume access to the utility…

Machine Learning · Computer Science 2024-09-10 Jing Yuan , Shaojie Tang

Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the $\ell_1$-norm. However, several important learning applications cannot benefit from this approach as…

Machine Learning · Computer Science 2013-04-11 Anastasios Kyrillidis , Stephen Becker , Volkan Cevher and , Christoph Koch

Random features provide a practical framework for large-scale kernel approximation and supervised learning. It has been shown that data-dependent sampling of random features using leverage scores can significantly reduce the number of…

Machine Learning · Computer Science 2019-03-21 Shahin Shahrampour , Soheil Kolouri

Markovian population models are suitable abstractions to describe well-mixed interacting particle systems in situation where stochastic fluctuations are significant due to the involvement of low copy particles. In molecular biology,…

Quantitative Methods · Quantitative Biology 2014-01-17 Christoph Zechner , Federico Wadehn , Heinz Koeppl

We study high-dimensional Bayesian linear regression with a general beta prime distribution for the scale parameter. Under the assumption of sparsity, we show that appropriate selection of the hyperparameters in the beta prime prior leads…

Methodology · Statistics 2019-07-19 Ray Bai , Malay Ghosh

One of the crucial tasks in many inference problems is the extraction of sparse information out of a given number of high-dimensional measurements. In machine learning, this is frequently achieved using, as a penality term, the $L_p$ norm…

Disordered Systems and Neural Networks · Physics 2012-02-09 Alejandro Lage-Castellanos , Andrea Pagnani , Martin Weigt

We study the problem of selecting a subset of k random variables from a large set, in order to obtain the best linear prediction of another variable of interest. This problem can be viewed in the context of both feature selection and sparse…

Machine Learning · Statistics 2011-02-28 Abhimanyu Das , David Kempe

We introduce a statistical physics inspired supervised machine learning algorithm for classification and regression problems. The method is based on the invariances or stability of predicted results when known data is represented as…

Machine Learning · Statistics 2018-11-19 Patrick Chao , Tahereh Mazaheri , Bo Sun , Nicholas B. Weingartner , Zohar Nussinov

We investigate fast methods that allow to quickly eliminate variables (features) in supervised learning problems involving a convex loss function and a $l_1$-norm penalty, leading to a potentially substantial reduction in the number of…

Machine Learning · Computer Science 2010-10-28 Laurent El Ghaoui , Vivian Viallon , Tarek Rabbani

The idea that many important classes of signals can be well-represented by linear combinations of a small set of atoms selected from a given dictionary has had dramatic impact on the theory and practice of signal processing. For practical…

Information Theory · Computer Science 2015-03-18 Quan Geng , Huan Wang , John Wright

Adapting Vision-Language Models (VLMs) to new domains with few labeled samples remains a significant challenge due to severe overfitting and computational constraints. State-of-the-art solutions, such as low-rank reparameterization,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Nairouz Mrabah , Nicolas Richet , Ismail Ben Ayed , Éric Granger

Achieving sample efficiency in online episodic reinforcement learning (RL) requires optimally balancing exploration and exploitation. When it comes to a finite-horizon episodic Markov decision process with $S$ states, $A$ actions and…

Machine Learning · Computer Science 2022-10-18 Gen Li , Laixi Shi , Yuxin Chen , Yuejie Chi