paper-with-me

홈 › Papers

On Making Stochastic Classifiers Deterministic

2019-12-01 · NeurIPS 2019 12 · Andrew Cotter, Maya Gupta, Harikrishna Narasimhan

Stochastic classifiers arise in a number of machine learning problems, and have become especially prominent of late, as they often result from constrained optimization problems, e.g. for fairness, churn, or custom losses. Despite their utility, the inherent randomness of stochastic classifiers may cause them to be problematic to use in practice for a variety of practical reasons. In this paper, we attempt to answer the theoretical question of how well a stochastic classifier can be approximated by a deterministic one, and compare several different approaches, proving lower and upper bounds. We also experimentally investigate the pros and cons of these methods, not only in regard to how successfully each deterministic classifier approximates the original stochastic classifier, but also in terms of how well each addresses the other issues that can make stochastic classifiers undesirable.

📄 PDF Abstract BibTeX

Code (1)

google-research/google-research 공식 구현 tf

Tasks

Fairness

Similar Papers 제목 키워드 기반

A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votes

2025-10-29 · Benjamin Leblanc, Pascal Germain arxiv

PAC-Bayes is a popular and efficient framework for obtaining generalization guarantees in situations involving uncountable hypothesis spaces. Unfortunately, in its classical formulation, it only provides guarantees on th…

PAC-Bayesian Generalization Guarantees for Fairness on Stochastic and Deterministic Classifiers

2026-02-12 · Julien Bastian, Benjamin Leblanc, Pascal Germain, Amaury Habrard 외 arxiv

Classical PAC generalization bounds on the prediction risk of a classifier are insufficient to provide theoretical guarantees on fairness when the goal is to learn models balancing predictive risk and fairness constraint…

On the disintegration of the stochastic majority vote: From PAC-Bayesian bounds to a self-bounding algorithm

2026-09-15 · Julien Bastian, Benjamin Leblanc, Pascal Germain, Amaury Habrard 외 arxiv

Weighted majority votes are central to many successful ensemble methods. PAC-Bayesian theory provides tight generalization guarantees for such models by analyzing the expected risk of stochastic classifiers, while analyz…

Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions

2025-02-09 · Can Cömer, Jannis Blüml, Cedric Derstroff, Kristian Kersting

Monte Carlo Tree Search (MCTS) has proven effective in solving decision-making problems in perfect information settings. However, its application to stochastic and imperfect information domains remains limited. This pape…

Decision Making

Counterfactually Comparing Abstaining Classifiers

2023-05-17 · NeurIPS 2023 11 · Yo Joong Choe, Aditya Gangrade, Aaditya Ramdas

Abstaining classifiers have the option to abstain from making predictions on inputs that they are unsure about. These classifiers are becoming increasingly popular in high-stakes decision-making problems, as they can wit…

Causal InferencecounterfactualDecision Making