English
Related papers

Related papers: Data-Free/Data-Sparse Softmax Parameter Estimation…

200 papers

We present a novel self-taught framework for unsupervised metric learning, which alternates between predicting class-equivalence relations between data through a moving average of an embedding model and learning the model with the predicted…

Computer Vision and Pattern Recognition · Computer Science 2022-05-05 Sungyeon Kim , Dongwon Kim , Minsu Cho , Suha Kwak

Transformers can perform in-context classification from a few labeled examples, yet the inference-time algorithm remains opaque. We study multi-class linear classification in the hard no-margin regime and make the computation identifiable…

Machine Learning · Computer Science 2026-04-20 Patrick Lutz , Themistoklis Haris , Arjun Chandra , Aditya Gangrade , Venkatesh Saligrama

Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and…

Machine Learning · Computer Science 2015-02-24 Yichuan Tang

We estimate convex polytopes and general convex sets in $\mathbb R^d,d\geq 2$ in the regression framework. We measure the risk of our estimators using a $L^1$-type loss function and prove upper bounds on these risks. We show that, in the…

Statistics Theory · Mathematics 2012-11-16 Victor-Emmanuel Brunel

Many high dimensional sparse learning problems are formulated as nonconvex optimization. A popular approach to solve these nonconvex optimization problems is through convex relaxations such as linear and semidefinite programming. In this…

Machine Learning · Statistics 2015-03-17 Zhaoran Wang , Quanquan Gu , Han Liu

We propose a flexible convex relaxation for the phase retrieval problem that operates in the natural domain of the signal. Therefore, we avoid the prohibitive computational cost associated with "lifting" and semidefinite programming (SDP)…

Information Theory · Computer Science 2017-03-17 Sohail Bahmani , Justin Romberg

This paper investigates projection-free algorithms for stochastic constrained multi-level optimization. In this context, the objective function is a nested composition of several smooth functions, and the decision set is closed and convex.…

Optimization and Control · Mathematics 2024-06-07 Wei Jiang , Sifan Yang , Wenhao Yang , Yibo Wang , Yuanyu Wan , Lijun Zhang

We consider regression with square loss and general classes of functions without the boundedness assumption. We introduce a notion of offset Rademacher complexity that provides a transparent way to study localization both in expectation and…

Machine Learning · Statistics 2020-07-27 Tengyuan Liang , Alexander Rakhlin , Karthik Sridharan

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

We consider the problem of estimating how well a model class is capable of fitting a distribution of labeled data. We show that it is often possible to accurately estimate this "learnability" even when given an amount of data that is too…

Machine Learning · Computer Science 2019-03-26 Weihao Kong , Gregory Valiant

Learning distributed representations, or embeddings, that encode the relational similarity patterns among objects is a relevant task in machine learning. A popular method to learn the embedding matrices $X, Y$ is optimizing a loss function…

Machine Learning · Computer Science 2025-06-03 Lorenzo Dall'Amico , Enrico Maria Belliardo

Learning image representations on decentralized data can bring many benefits in cases where data cannot be aggregated across data silos. Softmax cross entropy loss is highly effective and commonly used for learning image representations.…

Machine Learning · Computer Science 2022-03-10 Sagar M. Waghmare , Hang Qi , Huizhong Chen , Mikhail Sirotenko , Tomer Meron

Recent neural network and language models rely on softmax distributions with an extremely large number of categories. Since calculating the softmax normalizing constant in this context is prohibitively expensive, there is a growing…

Machine Learning · Statistics 2018-03-26 Francois Fagan , Garud Iyengar

The basic question of delineating those statistical problems that are solvable without making any assumptions on the underlying data distribution has long animated statistics and learning theory. This paper characterizes when a convex…

Statistics Theory · Mathematics 2025-08-27 Felipe Areces , John C. Duchi

In this paper, we propose a simple, versatile model for learning the structure and parameters of multivariate distributions from a data set. Learning a Markov network from a given data set is not a simple problem, because Markov networks…

Machine Learning · Computer Science 2012-06-19 Kazuya Takabatake , Shotaro Akaho

Recently, several works have shown that natural modifications of the classical conditional gradient method (aka Frank-Wolfe algorithm) for constrained convex optimization, provably converge with a linear rate when: i) the feasible set is a…

Optimization and Control · Mathematics 2016-05-23 Dan Garber , Ofer Meshi

With an eye towards human-centered automation, we contribute to the development of a systematic means to infer features of human decision-making from behavioral data. Motivated by the common use of softmax selection in models of human…

Optimization and Control · Mathematics 2015-09-01 Paul Reverdy , Naomi E. Leonard

The success of deep neural networks greatly relies on the availability of large amounts of high-quality annotated data, which however are difficult or expensive to obtain. The resulting labels may be class imbalanced, noisy or human biased.…

Machine Learning · Computer Science 2022-06-24 Xiong Zhou , Xianming Liu , Deming Zhai , Junjun Jiang , Xin Gao , Xiangyang Ji

We introduce a method for proving lower bounds on the efficacy of semidefinite programming (SDP) relaxations for combinatorial problems. In particular, we show that the cut, TSP, and stable set polytopes on $n$-vertex graphs are not the…

Computational Complexity · Computer Science 2014-11-25 James R. Lee , Prasad Raghavendra , David Steurer

We revisit Deep Linear Discriminant Analysis (Deep LDA) from a likelihood-based perspective. While classical LDA is a simple Gaussian model with linear decision boundaries, attaching an LDA head to a neural encoder raises the question of…

Machine Learning · Statistics 2026-02-23 Maxat Tezekbayev , Arman Bolatov , Zhenisbek Assylbekov