English
Related papers

Related papers: Stable Training of Probabilistic Models Using the …

200 papers

We consider the problem of constructing a least conservative estimator of the expected value $\mu$ of a non-negative heavy-tailed random variable. We require that the probability of overestimating the expected value $\mu$ is kept…

Optimization and Control · Mathematics 2026-04-21 Bart P. G. van Parys , Bert Zwart

Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs) through increased test-time computation. Current state-of-the-art methods often employ computationally intensive reward models…

Computation and Language · Computer Science 2025-12-15 Zhewei Kang , Xuandong Zhao , Dawn Song

Preference optimization is widely used to align Large Language Models (LLMs) with preference feedback. However, most existing methods train on a single positive-negative pair per prompt, discarding additional supervision available in…

Computation and Language · Computer Science 2026-04-20 Jixuan Leng , Si Si , Hsiang-Fu Yu , Vinod Raman , Inderjit S. Dhillon

There has been substantial progress in the inference of formal behavioural specifications from sample trajectories, for example, using Linear Temporal Logic (LTL). However, these techniques cannot handle specifications that correctly…

Logic in Computer Science · Computer Science 2025-05-20 Rajarshi Roy , Yash Pote , David Parker , Marta Kwiatkowska

We introduce an analytical framework to quantify the changes in a machine learning algorithm's output distribution following the inclusion of a few data points in its training set, a notion we define as leave-one-out distinguishability…

Machine Learning · Computer Science 2024-04-18 Jiayuan Ye , Anastasia Borovykh , Soufiane Hayou , Reza Shokri

Language models are generally trained on data spanning a wide range of topics (e.g., news, reviews, fiction), but they might be applied to an a priori unknown target distribution (e.g., restaurant reviews). In this paper, we first show that…

Computation and Language · Computer Science 2019-09-06 Yonatan Oren , Shiori Sagawa , Tatsunori B. Hashimoto , Percy Liang

Consider a Markov decision process (MDP) that admits a set of state-action features, which can linearly express the process's probabilistic transition model. We propose a parametric Q-learning algorithm that finds an approximate-optimal…

Machine Learning · Computer Science 2019-06-07 Lin F. Yang , Mengdi Wang

Learning and compression are driven by the common aim of identifying and exploiting statistical regularities in data, which opens the door for fertile collaboration between these areas. A promising group of compression techniques for…

Machine Learning · Computer Science 2021-02-02 Fernando E. Rosas , Pedro A. M. Mediano , Michael Gastpar

When some parameters of a constrained optimization problem (COP) are uncertain, this gives rise to a predict-then-optimize (PtO) problem, comprising two stages: the prediction of the unknown parameters from contextual information and the…

Machine Learning · Computer Science 2025-10-28 Jayanta Mandi , Marianne Defresne , Senne Berden , Tias Guns

We study zeroth-order optimization where solutions must minimize a cost $d(s)$ while maintaining high probability under a complex generative prior $L(s)$ (e.g., a parameterized model). This reduces to sampling from a target distribution…

Machine Learning · Computer Science 2026-05-06 Pranjal Awasthi , Sreenivas Gollapudi , Ravi Kumar , Kamesh Munagala

Robust Markov Decision Processes (MDPs) are a powerful framework for modeling sequential decision-making problems with model uncertainty. This paper proposes the first first-order framework for solving robust MDPs. Our algorithm interleaves…

Optimization and Control · Mathematics 2021-01-18 Julien Grand-Clément , Christian Kroer

Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any…

Machine Learning · Computer Science 2020-11-24 Tianhe Yu , Garrett Thomas , Lantao Yu , Stefano Ermon , James Zou , Sergey Levine , Chelsea Finn , Tengyu Ma

Mechanistic network models specify the mechanisms by which networks grow and change, allowing researchers to investigate complex systems using both simulation and analytical techniques. Unfortunately, it is difficult to write likelihoods…

Methodology · Statistics 2023-07-19 Jonathan Larson , Jukka-Pekka Onnela

Mixture of autoregressions (MoAR) models provide a model-based approach to the clustering of time series data. The maximum likelihood (ML) estimation of MoAR models requires the evaluation of products of large numbers of densities of normal…

Computation · Statistics 2016-10-19 Hien D Nguyen , Geoffrey J McLachlan , Pierre Orban , Pierre Bellec , Andrew L Janke

Although the log-likelihood is widely used in model selection, the log-likelihood ratio has had few applications in this area. We develop a log-likelihood ratio based method for selecting regression models by focusing on the set of models…

Methodology · Statistics 2021-09-28 Min Tsao

Shallow ensembles provide a convenient strategy for uncertainty quantification in machine learning interatomic potentials, that is computationally efficient because the different ensemble members share a large part of the model weights. In…

Chemical Physics · Physics 2026-02-18 Moritz Schäfer , Matthias Kellner , Johannes Kästner , Michele Ceriotti

Model inference, such as model comparison, model checking, and model selection, is an important part of model development. Leave-one-out cross-validation (LOO) is a general approach for assessing the generalizability of a model, but…

Machine Learning · Statistics 2020-08-12 Måns Magnusson , Michael Riis Andersen , Johan Jonasson , Aki Vehtari

The Lopsided Lov\'{a}sz Local Lemma (LLLL) is a powerful probabilistic principle which has been used in a variety of combinatorial constructions. While originally a general statement about probability spaces, it has recently been…

Data Structures and Algorithms · Computer Science 2023-10-13 David G. Harris

This paper develops a new family of estimators, the minimum density power divergence estimators (MDPDEs), for the parameters of the one-shot device model as well as a new family of test statistics, Z-type test statistics based on MDPDEs,…

Methodology · Statistics 2017-04-27 N. Balakrishnan , E. Castilla , N. Martin , L. Pardo

Log-Structured Merge trees (LSM trees) are increasingly used as the storage engines behind several data systems, frequently deployed in the cloud. Similar to other database architectures, LSM trees take into account information about the…

Databases · Computer Science 2021-11-04 Andy Huynh , Harshal A. Chaudhari , Evimaria Terzi , Manos Athanassoulis
‹ Prev 1 8 9 10 Next ›