English
Related papers

Related papers: Fast and Multiphase Rates for Nearest Neighbor Cla…

200 papers

Industry practitioners care about small improvements in malware detection accuracy because their models are deployed to hundreds of millions of machines, meaning a 0.1\% change can cause an overwhelming number of false positives. However,…

Machine Learning · Computer Science 2023-12-27 Tirth Patel , Fred Lu , Edward Raff , Charles Nicholas , Cynthia Matuszek , James Holt

Training large language models (LLMs) is computationally expensive, partly because the loss exhibits slow power-law convergence whose origin remains debatable. Through systematic analysis of toy models and empirical evaluation of LLMs, we…

Machine Learning · Computer Science 2026-02-04 Yizhou Liu , Ziming Liu , Cengiz Pehlevan , Jeff Gore

Learning rate schedule has a major impact on the performance of deep learning models. Still, the choice of a schedule is often heuristical. We aim to develop a precise understanding of the effects of different learning rate schedules and…

Machine Learning · Computer Science 2020-02-25 Guillaume Leclerc , Aleksander Madry

Inspired by recent research that recommends starting neural networks training with large learning rates (LRs) to achieve the best generalization, we explore this hypothesis in detail. Our study clarifies the initial LR ranges that provide…

Machine Learning · Computer Science 2023-11-21 Ekaterina Lobacheva , Eduard Pockonechnyy , Maxim Kodryan , Dmitry Vetrov

Stochastic Approximation (SA) is a widely used algorithmic approach in various fields, including optimization and reinforcement learning (RL). Among RL algorithms, Q-learning is particularly popular due to its empirical success. In this…

Machine Learning · Statistics 2024-01-26 Yixuan Zhang , Qiaomin Xie

Theoretical studies on transfer learning or domain adaptation have so far focused on situations with a known hypothesis class or model; however in practice, some amount of model selection is usually involved, often appearing under the…

Machine Learning · Statistics 2023-10-13 Steve Hanneke , Samory Kpotufe , Yasaman Mahdaviyeh

In multiple classification, one aims to determine whether a testing sequence is generated from the same distribution as one of the M training sequences or not. Unlike most of existing studies that focus on discrete-valued sequences with…

Machine Learning · Statistics 2024-10-30 Lina Zhu , Lin Zhou

This manuscript studies statistical properties of linear classifiers obtained through minimization of an unregularized convex risk over a finite sample. Although the results are explicitly finite-dimensional, inputs may be passed through…

Machine Learning · Computer Science 2012-06-15 Matus Telgarsky

Unsupervised classification methods learn a discriminative classifier from unlabeled data, which has been proven to be an effective way of simultaneously clustering the data and training a classifier from the data. Various unsupervised…

Machine Learning · Computer Science 2013-05-23 Yingzhen Yang , Thomas S. Huang

Neural networks are typically trained with a single learning rate across all layers. While recent empirical evidence suggests that assigning layer-specific learning rates can accelerate training, a principled understanding of the conditions…

Machine Learning · Computer Science 2026-05-26 Sihan Zeng , Sujay Bhatt , Sumitra Ganesh

What advantage do \emph{sequential} procedures provide over batch algorithms for testing properties of unknown distributions? Focusing on the problem of testing whether two distributions $\mathcal{D}_1$ and $\mathcal{D}_2$ on $\{1,\dots,…

Data Structures and Algorithms · Computer Science 2022-05-13 Omar Fawzi , Nicolas Flammarion , Aurélien Garivier , Aadil Oufkir

Stochastic gradient descent with a large initial learning rate is widely used for training modern neural net architectures. Although a small initial learning rate allows for faster training and better test performance initially, the large…

Machine Learning · Computer Science 2020-04-28 Yuanzhi Li , Colin Wei , Tengyu Ma

Research on nearest-neighbor methods tends to focus somewhat dichotomously either on the statistical or the computational aspects -- either on, say, Bayes consistency and rates of convergence or on techniques for speeding up the proximity…

Statistics Theory · Mathematics 2020-04-17 Klim Efremenko , Aryeh Kontorovich , Moshe Noivirt

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

We present a limited empirical study of scaling laws for transfer learning in transformer models. More specifically, we examine a scaling law that incorporates a "transfer gap" term, indicating the effectiveness of pre-training on one…

Machine Learning · Computer Science 2024-09-02 Matthew Barnett

Distribution regression seeks to estimate the conditional distribution of a multivariate response given a continuous covariate. This approach offers a more complete characterization of dependence than traditional regression methods.…

Statistics Theory · Mathematics 2025-06-10 Rong Tang , Yun Yang

The machine learning community has become increasingly concerned with the potential for bias and discrimination in predictive models. This has motivated a growing line of work on what it means for a classification procedure to be "fair." In…

Machine Learning · Computer Science 2017-11-07 Geoff Pleiss , Manish Raghavan , Felix Wu , Jon Kleinberg , Kilian Q. Weinberger

Recent works have highlighted optimization difficulties faced by gradient descent in training the first and last layers of transformer-based language models, which are overcome by optimizers such as Adam. These works suggest that the…

Machine Learning · Computer Science 2025-05-27 Frederik Kunstner , Francis Bach

In a wide range of statistical learning problems such as ranking, clustering or metric learning among others, the risk is accurately estimated by $U$-statistics of degree $d\geq 1$, i.e. functionals of the training data with low variance…

Machine Learning · Statistics 2019-01-25 Stéphan Clémençon , Aurélien Bellet , Igor Colin

ML models are typically trained using large datasets of high quality. However, training datasets often contain inconsistent or incomplete data. To tackle this issue, one solution is to develop algorithms that can check whether a prediction…

Machine Learning · Computer Science 2022-01-19 Austen Z. Fan , Paraschos Koutris
‹ Prev 1 8 9 10 Next ›