English
Related papers

Related papers: Divergence and Sufficiency for Convex Optimization

200 papers

Logarithmic score and information divergence appear in both information theory, statistics, statistical mechanics, and portfolio theory. We demonstrate that all these topics involve some kind of optimization that leads directly to the use…

Statistics Theory · Mathematics 2015-07-28 Peter Harremoës

It is well-known that there are a number of relations between theoretical finance theory and information theory. Some of these relations are exact and some are approximate. In this paper we will explore some of these relations and determine…

Information Theory · Computer Science 2016-01-29 Peter Harremoës

The regret bound of an optimization algorithms is one of the basic criteria for evaluating the performance of the given algorithm. By inspecting the differences between the regret bounds of traditional algorithms and adaptive one, we…

Machine Learning · Statistics 2017-07-07 HyoungSeok Kim , JiHoon Kang , WooMyoung Park , SukHyun Ko , YoonHo Cho , DaeSung Yu , YoungSook Song , JungWon Choi

In the last several years, the intimate connection between convex optimization and learning problems, in both statistical and sequential frameworks, has shifted the focus of algorithmic machine learning to examine this interplay. In…

Machine Learning · Computer Science 2014-07-23 Mehrdad Mahdavi

The performance measure of an algorithm is a crucial part of its analysis. The performance can be determined by the study on the convergence rate of the algorithm in question. It is necessary to study some (hopefully convergent) sequence…

Optimization and Control · Mathematics 2016-07-25 Sandra Astete-Morales , Marie-Liesse Cauwet , Olivier Teytaud

We consider algorithms for "smoothed online convex optimization" problems, a variant of the class of online convex optimization problems that is strongly related to metrical task systems. Prior literature on these problems has focused on…

Data Structures and Algorithms · Computer Science 2015-08-18 Lachlan L. H. Andrew , Siddharth Barman , Katrina Ligett , Minghong Lin , Adam Meyerson , Alan Roytman , Adam Wierman

Bregman divergences are a class of distance-like comparison functions which play fundamental roles in optimization, statistics, and information theory. One important property of Bregman divergences is that they cause two useful formulations…

Information Theory · Computer Science 2025-01-07 Philip S. Chodrow

The performance of online convex optimization algorithms in a dynamic environment is often expressed in terms of the dynamic regret, which measures the decision maker's performance against a sequence of time-varying comparators. In the…

Machine Learning · Computer Science 2022-02-28 Nima Eshraghi , Ben Liang

Approximations of optimization problems arise in computational procedures and sensitivity analysis. The resulting effect on solutions can be significant, with even small approximations of components of a problem translating into large…

Optimization and Control · Mathematics 2022-08-10 Johannes O. Royset

We investigate online convex optimization in changing environments, and choose the adaptive regret as the performance measure. The goal is to achieve a small regret over every interval so that the comparator is allowed to change over time.…

Machine Learning · Computer Science 2019-06-18 Lijun Zhang , Tie-Yan Liu , Zhi-Hua Zhou

The logarithmic divergence is an extension of the Bregman divergence motivated by optimal transport and a generalized convex duality, and satisfies many remarkable properties. Using the geometry induced by the logarithmic divergence, we…

Optimization and Control · Mathematics 2022-09-08 Amanjit Singh Kainth , Ting-Kam Leonard Wong , Frank Rudzicz

A loss function measures the discrepancy between the true values and their estimated fits, for a given instance of data. In classification problems, a loss function is said to be proper if a minimizer of the expected loss is the true…

Information Theory · Computer Science 2020-01-03 Amichai Painsky , Gregory W. Wornell

Recently, much work has been done on extending the scope of online learning and incremental stochastic optimization algorithms. In this paper we contribute to this effort in two ways: First, based on a new regret decomposition and a…

Machine Learning · Computer Science 2017-09-12 Pooria Joulani , András György , Csaba Szepesvári

We consider assortment optimization over a continuous spectrum of products represented by the unit interval, where the seller's problem consists of determining the optimal subset of products to offer to potential customers. To describe the…

Machine Learning · Statistics 2021-04-15 Yannik Peeters , Arnoud V. den Boer , Michel Mandjes

The menu-dependent nature of regret-minimization creates subtleties when it is applied to dynamic decision problems. Firstly, it is not clear whether \emph{forgone opportunities} should be included in the \emph{menu}, with respect to which…

Artificial Intelligence · Computer Science 2015-06-19 Joseph Y. Halpern , Samantha Leung

We develop new approaches in multi-class settings for constructing proper scoring rules and hinge-like losses and establishing corresponding regret bounds with respect to the zero-one or cost-weighted classification loss. Our construction…

Statistics Theory · Mathematics 2021-05-18 Zhiqiang Tan , Xinwei Zhang

Personalized alignment aims to adapt large language models to heterogeneous user preferences, yet the precise theoretical conditions for its statistical efficiency have not been formally established. This paper characterizes the conditions…

Machine Learning · Computer Science 2026-05-12 Enoch Hyunwook Kang

We introduce a bottleneck method for learning data representations based on information deficiency, rather than the more traditional information sufficiency. A variational upper bound allows us to implement this method efficiently. The…

Information Theory · Computer Science 2020-11-05 Pradeep Kr. Banerjee , Guido Montúfar

In this short note we derive a relationship between the Bregman divergence from the current policy to the optimal policy and the suboptimality of the current value function in a regularized Markov decision process. This result has…

Machine Learning · Computer Science 2022-11-08 Brendan O'Donoghue

We consider regret minimization in repeated games with non-convex loss functions. Minimizing the standard notion of regret is computationally intractable. Thus, we define a natural notion of regret which permits efficient optimization and…

Machine Learning · Computer Science 2017-11-06 Elad Hazan , Karan Singh , Cyril Zhang
‹ Prev 1 2 3 10 Next ›