English
Related papers

Related papers: Occam's Razor is Only as Sharp as Your ELBO

200 papers

Modern deep learning models are usually highly over-parameterized so that they can overfit the training data. Surprisingly, such overfitting neural networks can usually still achieve high prediction accuracy. To study this "benign…

Machine Learning · Computer Science 2023-10-04 Xuran Meng , Difan Zou , Yuan Cao

Input-output maps are prevalent throughout science and technology. They are empirically observed to be biased towards simple outputs, but we don't understand why. To address this puzzle, we study the archetypal input-output map: a…

Disordered Systems and Neural Networks · Physics 2026-03-03 Thomas M. A. Fink

We consider a PAC-Bayes type learning rule for binary classification, balancing the training error of a randomized ''posterior'' predictor with its KL divergence to a pre-specified ''prior''. This can be seen as an extension of a modified…

Machine Learning · Statistics 2026-03-25 Xiaohan Zhu , Mesrob I. Ohannessian , Nathan Srebro

In this expository note we describe a surprising phenomenon in overparameterized linear regression, where the dimension exceeds the number of samples: there is a regime where the test risk of the estimator found by gradient descent…

Machine Learning · Statistics 2019-12-17 Preetum Nakkiran

This work introduces a new method for selecting the number of components in finite mixture models (FMMs) using variational Bayes, inspired by the large-sample properties of the Evidence Lower Bound (ELBO) derived from mean-field (MF)…

Methodology · Statistics 2026-04-23 Chenyang Wang , Yun Yang

This paper provides an analysis of the tradeoff between asymptotic bias (suboptimality with unlimited data) and overfitting (additional suboptimality due to limited data) in the context of reinforcement learning with partial observability.…

Machine Learning · Statistics 2019-02-07 Vincent Francois-Lavet , Guillaume Rabusseau , Joelle Pineau , Damien Ernst , Raphael Fonteneau

This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on the fact that…

Machine Learning · Computer Science 2020-11-10 Botao Hao , Yaqi Duan , Tor Lattimore , Csaba Szepesvári , Mengdi Wang

Exploration is a crucial aspect of bandit and reinforcement learning algorithms. The uncertainty quantification necessary for exploration often comes from either closed-form expressions based on simple models or resampling and posterior…

Machine Learning · Computer Science 2021-10-07 James McInerney , Nathan Kallus

Addressing selection bias in latent variable causal discovery is important yet underexplored, largely due to a lack of suitable statistical tools: While various tools beyond basic conditional independencies have been developed to handle…

Machine Learning · Computer Science 2025-12-15 Haoyue Dai , Yiwen Qiu , Ignavier Ng , Xinshuai Dong , Peter Spirtes , Kun Zhang

The algorithms available for retail forecasting have increased in complexity. Newer methods, such as machine learning, are inherently complex. The more traditional families of forecasting models, such as exponential smoothing and…

Methodology · Statistics 2023-10-23 Fotios Petropoulos , Yael Grushka-Cockayne , Enno Siemsen , Evangelos Spiliotis

Least-squares refitting is widely used in high dimensional regression to reduce the prediction bias of l1-penalized estimators (e.g., Lasso and Square-Root Lasso). We present theoretical and numerical results that provide new insights into…

Methodology · Statistics 2013-06-04 Johannes Lederer

Matrix approximation is a common tool in machine learning for building accurate prediction models for recommendation systems, text mining, and computer vision. A prevalent assumption in constructing matrix approximations is that the…

Machine Learning · Computer Science 2013-01-16 Joonseok Lee , Seungyeon Kim , Guy Lebanon , Yoram Singer

Occam's Razor tells us to pick the simplest model that fits our observations. In order to make sense of his process mathematically, we interpret it in the context of posets of functions. Our approach leads to some unusual new combinatorial…

Combinatorics · Mathematics 2015-04-29 William Ralph

The recent success of neural network models has shone light on a rather surprising statistical phenomenon: statistical models that perfectly fit noisy data can generalize well to unseen test data. Understanding this phenomenon of…

Machine Learning · Statistics 2022-09-13 Niladri S. Chatterji , Philip M. Long , Peter L. Bartlett

A commonly observed pattern in machine learning models is an underprediction of the target feature, with the model's predicted target rate for members of a given category typically being lower than the actual target rate for members of that…

Machine Learning · Computer Science 2023-07-06 Owen O'Neill , Fintan Costello

We consider the fundamental problem of estimating the mean of a vector $y=X\beta+z$, where $X$ is an $n\times p$ design matrix in which one can have far more variables than observations, and $z$ is a stochastic error term--the so-called…

Statistics Theory · Mathematics 2009-08-21 Emmanuel J. Candès , Yaniv Plan

The application of Bayesian inference for the purpose of model selection is very popular nowadays. In this framework, models are compared through their marginal likelihoods, or their quotients, called Bayes factors. However, marginal…

Methodology · Statistics 2022-07-27 F. Llorente , L. Martino , E. Curbelo , J. Lopez-Santiago , D. Delgado

Identifying optimal values for a high-dimensional set of hyperparameters is a problem that has received growing attention given its importance to large-scale machine learning applications such as neural architecture search. Recently…

We address the overlooked unbiasedness in existing long-tailed classification methods: we find that their overall improvement is mostly attributed to the biased preference of tail over head, as the test distribution is assumed to be…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Beier Zhu , Yulei Niu , Xian-Sheng Hua , Hanwang Zhang

One of the main current challenges in itemset mining is to discover a small set of high-quality itemsets. In this paper we propose a new and general approach for measuring the quality of itemsets. The method is solidly founded in Bayesian…

Databases · Computer Science 2019-02-12 Nikolaj Tatti