English
Related papers

Related papers: From Stochastic Mixability to Fast Rates

200 papers

A fundamental challenge in continual learning is to balance the trade-off between learning new tasks and remembering the previously acquired knowledge. Gradient Episodic Memory (GEM) achieves this balance by utilizing a subset of past…

Machine Learning · Computer Science 2024-10-02 Bo Liu , Mao Ye , Peter Stone , Qiang Liu

To deal with very large datasets a mini-batch version of the Monte Carlo Markov Chain Stochastic Approximation Expectation-Maximization algorithm for general latent variable models is proposed. For exponential models the algorithm is shown…

Computation · Statistics 2023-08-30 Tabea Rebafka , Estelle Kuhn , Catherine Matias

We develop minimax optimal risk bounds for the general learning task consisting in predicting as well as the best function in a reference set G up to the smallest possible additive term, called the convergence rate. When the reference set…

Statistics Theory · Mathematics 2008-03-04 Jean-Yves Audibert

We study risk-sensitive reinforcement learning in finite discounted MDPs with recursive entropic risk measures (ERM), where the risk parameter $\beta \neq 0$ controls the agent's risk attitude: $\beta>0$ for risk-averse and $\beta<0$ for…

Machine Learning · Computer Science 2026-05-20 Oliver Mortensen , Mohammad Sadegh Talebi

We consider the learning task consisting in predicting as well as the best function in a finite reference set G up to the smallest possible additive term. If R(g) denotes the generalization error of a prediction function g, under reasonable…

Statistics Theory · Mathematics 2007-06-13 Jean-Yves Audibert

Modern data-driven and distributed learning frameworks deal with diverse massive data generated by clients spread across heterogeneous environments. Indeed, data heterogeneity is a major bottleneck in scaling up many distributed learning…

Machine Learning · Computer Science 2023-08-23 Amirhossein Reisizadeh , Khashayar Gatmiry , Asuman Ozdaglar

Mixture models are a fundamental tool in applied statistics and machine learning for treating data taken from multiple subpopulations. The current practice for estimating the parameters of such models relies on local search heuristics…

Machine Learning · Computer Science 2012-09-07 Animashree Anandkumar , Daniel Hsu , Sham M. Kakade

We study robust linear regression in high-dimension, when both the dimension $d$ and the number of data points $n$ diverge with a fixed ratio $\alpha=n/d$, and study a data model that includes outliers. We provide exact asymptotics for the…

Machine Learning · Statistics 2024-06-24 Matteo Vilucchio , Emanuele Troiani , Vittorio Erba , Florent Krzakala

The estimation of rare event probabilities plays a pivotal role in diverse fields. Our aim is to determine the probability of a hazard or system failure occurring when a quantity of interest exceeds a critical value. In our approach, the…

Methodology · Statistics 2025-04-11 Lea Friedli , David Ginsbourger , Arnaud Doucet , Niklas Linde

We address the problem of solving mixed random linear equations. We have unlabeled observations coming from multiple linear regressions, and each observation corresponds to exactly one of the regression models. The goal is to learn the…

Machine Learning · Statistics 2020-08-13 Avishek Ghosh , Kannan Ramchandran

Exponential tilting is a technique commonly used in fields such as statistics, probability, information theory, and optimization to create parametric distribution shifts. Despite its prevalence in related fields, tilting has not seen…

Machine Learning · Computer Science 2023-06-02 Tian Li , Ahmad Beirami , Maziar Sanjabi , Virginia Smith

We consider the problem of learning a model from multiple heterogeneous sources with the goal of performing well on a new target distribution. The goal of learner is to mix these data sources in a target-distribution aware way and…

Machine Learning · Computer Science 2023-11-14 Yuyang Deng , Ilja Kuzborskij , Mehrdad Mahdavi

Fine-tuning large language models (LLM) can be costly. Parameter-efficient fine-tuning (PEFT) addresses the problems by training a fraction of the parameters, whose success reveals the expressiveness and flexibility of pretrained models.…

Machine Learning · Computer Science 2024-05-07 Jing Xu , Jingzhao Zhang

Empirical risk minimization (ERM) is sensitive to spurious correlations in the training data, which poses a significant risk when deploying systems trained under this paradigm in high-stake applications. While the existing literature…

Machine Learning · Computer Science 2023-10-31 Christos Tsirigotis , Joao Monteiro , Pau Rodriguez , David Vazquez , Aaron Courville

We explore a method of statistical estimation called Maximum Entropy on the Mean (MEM) which is based on an information-driven criterion that quantifies the compliance of a given point with a reference prior probability measure. At the core…

Statistics Theory · Mathematics 2022-12-20 Yakov Vaisbourd , Rustum Choksi , Ariel Goodwin , Tim Hoheisel , Carola-Bibiane Schönlieb

One of the classic data mining tasks is to discover bursts, time intervals, where events occur at abnormally high rate. In this paper we revisit Kleinberg's seminal work, where bursts are discovered by using exponential distribution with a…

Data Structures and Algorithms · Computer Science 2019-02-06 Nikolaj Tatti

The expectation-maximization (EM) algorithm and its variants are widely used in statistics. In high-dimensional mixture linear regression, the model is assumed to be a finite mixture of linear regression and the number of predictors is much…

Statistics Theory · Mathematics 2023-07-24 Ning Wang , Xin Zhang , Qing Mai

Mixture models serve as one fundamental tool with versatile applications. However, their training techniques, like the popular Expectation Maximization (EM) algorithm, are notoriously sensitive to parameter initialization and often suffer…

Machine Learning · Computer Science 2023-12-20 Yulai Cong , Sijia Li

Model usage is the central challenge of model-based reinforcement learning. Although dynamics model based on deep neural networks provide good generalization for single step prediction, such ability is over exploited when it is used to…

Machine Learning · Computer Science 2020-06-30 Chi Zhang , Sanmukh Rao Kuppannagari , Viktor K Prasanna

We study square loss in a realizable time-series framework with martingale difference noise. Our main result is a fast rate excess risk bound which shows that whenever a trajectory hypercontractivity condition holds, the risk of the…

Machine Learning · Computer Science 2024-06-14 Ingvar Ziemann , Stephen Tu