paper-with-me

홈 › Papers

Optimization and Regularization Under Arbitrary Objectives

2025-11-24 · Jared N. Lakhani, Etienne Pienaar arxiv

This study investigates the limitations of applying Markov Chain Monte Carlo (MCMC) methods to arbitrary objective functions, focusing on a two-block MCMC framework which alternates between Metropolis-Hastings and Gibbs sampling. While such approaches are often considered advantageous for enabling data-driven regularization, we show that their performance critically depends on the sharpness of the employed likelihood form. By introducing a sharpness parameter and exploring alternative likelihood formulations proportional to the target objective function, we demonstrate how likelihood curvature governs both in-sample performance and the degree of regularization inferred by the training data. Empirical applications are conducted on reinforcement learning tasks: including a navigation problem and the game of tic-tac-toe. The study concludes with a separate analysis examining the implications of extreme likelihood sharpness on arbitrary objective functions stemming from the classic game of blackjack, where the first block of the two-block MCMC framework is replaced with an iterative optimization step. The resulting hybrid approach achieves performance nearly identical to the original MCMC framework, indicating that excessive likelihood sharpness effectively collapses posterior mass onto a single dominant mode.

📄 PDF Abstract BibTeX arXiv:2511.19628

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Obtaining Adjustable Regularization for Free via Iterate Averaging

2020-08-15 · ICML 2020 1 · Jingfeng Wu, Vladimir Braverman, Lin F. Yang

Regularization for optimization is a crucial technique to avoid overfitting in machine learning. In order to obtain the best performance, we usually train a model by tuning the regularization parameters. It becomes costl…

Open-Ended Question Answering

Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization

2023-07-07 · Chris Kolb, Christian L. Müller, Bernd Bischl, David Rügamer

We present a framework for smooth optimization of explicitly regularized objectives for (structured) sparsity. These non-smooth and possibly non-convex problems typically rely on solvers tailored to specific models and r…

Sparse Learning

Unleashing Linear Optimizers for Group-Fair Learning and Optimization

2018-04-11 · Daniel Alabi, Nicole Immorlica, Adam Tauman Kalai

Most systems and learning algorithms optimize average performance or average loss -- one reason being computational complexity. However, many objectives of practical interest are more complex than simply average loss. Th…

Fairness

Universal generalization guarantees for Wasserstein distributionally robust models

2024-02-19 · Tam Le, Jérôme Malick

Distributionally robust optimization has emerged as an attractive way to train robust machine learning models, capturing data uncertainty and distribution shifts. Recent statistical analyses have proved that generalizati…

Latent Adversarial Regularization for Offline Preference Optimization

2026-01-29 · Enyi Jiang, Yibo Jacky Zhang, Yinglun Xu, Andreas Haupt 외 arxiv

Learning from human feedback typically relies on preference optimization that constrains policy updates through token-level regularization. However, preference optimization for language models is particularly challenging…