English
Related papers

Related papers: On the Properties of the Softmax Function with App…

200 papers

We investigate the convergence rates of the trajectories generated by implicit first and second order dynamical systems associated to the determination of the zeros of the sum of a maximally monotone operator and a monotone and Lipschitz…

Optimization and Control · Mathematics 2015-04-09 Radu Ioan Bot , Ernö Robert Csetnek

Reinforcement learning (RL) agents can leverage batches of previously collected data to extract a reasonable control policy. An emerging issue in this offline RL setting, however, is that the bootstrapping update underlying many of our…

Machine Learning · Computer Science 2023-04-20 Chenjun Xiao , Han Wang , Yangchen Pan , Adam White , Martha White

We address learning Nash equilibria in convex games under the payoff information setting. We consider the case in which the game pseudo-gradient is monotone but not necessarily strictly monotone. This relaxation of strict monotonicity…

Optimization and Control · Mathematics 2023-08-17 Tatiana Tatarenko , Maryam Kamgarpour

Latent categorical variables are frequently found in deep learning architectures. They can model actions in discrete reinforcement-learning environments, represent categories in latent-variable models, or express relations in graph neural…

Machine Learning · Computer Science 2026-05-14 Alessandro Manenti , Cesare Alippi

Two main families of reinforcement learning algorithms, Q-learning and policy gradients, have recently been proven to be equivalent when using a softmax relaxation on one part, and an entropic regularization on the other. We relate this…

Machine Learning · Computer Science 2017-12-27 Pierre H. Richemond , Brendan Maginnis

This paper proposes a novel fuzzy action selection method to leverage human knowledge in reinforcement learning problems. Based on the estimates of the most current action-state values, the proposed fuzzy nonlinear mapping as-signs each…

Artificial Intelligence · Computer Science 2021-06-15 Mohsen Annabestani , Ali Abedi , Mohammad Reza Nematollahi , Mohammad Bagher Naghibi Sis-tani

In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes the probability of a catastrophic failure. Unfortunately,…

Machine Learning · Computer Science 2021-03-01 Elita A. Lobo , Mohammad Ghavamzadeh , Marek Petrik

Smooth game optimization has recently attracted great interest in machine learning as it generalizes the single-objective optimization paradigm. However, game dynamics is more complex due to the interaction between different players and is…

Optimization and Control · Mathematics 2021-01-27 Guodong Zhang , Yuanhao Wang

In the past few years, Softmax has become a common component in neural network frameworks. In this paper, a gradient decay hyperparameter is introduced in Softmax to control the probability-dependent gradient decay rate during training. By…

Machine Learning · Statistics 2023-10-10 Siyuan Zhang , Linbo Xie , Ying Chen

Softmax function is widely used in artificial neural networks for multiclass classification, multilabel classification, attention mechanisms, etc. However, its efficacy is often questioned in literature. The log-softmax loss has been shown…

Machine Learning · Computer Science 2020-11-24 Kunal Banerjee , Vishak Prasad C , Rishi Raj Gupta , Karthik Vyas , Anushree H , Biswajit Mishra

Some variant of the Frank-Wolfe method for convex optimization problems with adaptive selection of the step parameter corresponding to information about the smoothness of the objective function (the Lipschitz constant of the gradient).…

Optimization and Control · Mathematics 2023-08-01 G. V. Aivazian , F. S. Stonyakin , D. A. Pasechnyuk , M. S. Alkousa , A. M. Raigorodskii

We study properties of programs with monotone and convex constraints. We extend to these formalisms concepts and results from normal logic programming. They include the notions of strong and uniform equivalence with their characterizations,…

Artificial Intelligence · Computer Science 2011-10-04 L. Liu , M. Truszczynski

We introduce a penalty term-based splitting algorithm with inertial effects designed for solving monotone inclusion problems involving the sum of maximally monotone operators and the convex normal cone to the (nonempty) set of zeros of a…

Optimization and Control · Mathematics 2015-12-15 Radu Ioan Bot , Ernö Robert Csetnek

Value function estimation is an important task in reinforcement learning, i.e., prediction. The Boltzmann softmax operator is a natural value estimator and can provide several benefits. However, it does not satisfy the non-expansion…

Machine Learning · Computer Science 2019-09-10 Ling Pan , Qingpeng Cai , Qi Meng , Wei Chen , Longbo Huang , Tie-Yan Liu

In this paper, we address the problem of interpolation of smooth convex-concave functions. Interpolation is a key step for computer-assisted estimation of worst-case performance via PEP-like techniques, and smooth convex-concave functions…

Optimization and Control · Mathematics 2026-05-26 Valery Krivchenko , Alexander Gasnikov , Dmitry Kovalev

In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation,…

Machine Learning · Statistics 2019-09-19 Ugo Tanielian , Flavian Vasile

We investigate the stochastic optimization problem of minimizing population risk, where the loss defining the risk is assumed to be weakly convex. Compositions of Lipschitz convex functions with smooth maps are the primary examples of such…

Optimization and Control · Mathematics 2018-12-19 Damek Davis , Dmitriy Drusvyatskiy

Deep neural networks are vulnerable to adversarial attacks. Recent studies about adversarial robustness focus on the loss landscape in the parameter space since it is related to optimization and generalization performance. These studies…

Machine Learning · Computer Science 2023-03-07 Sekitoshi Kanai , Masanori Yamada , Hiroshi Takahashi , Yuki Yamanaka , Yasutoshi Ida

This article studies the monotonicity, log-convexity of the modified Lommel functions by using its power series and infinite product representation. Same properties for the ratio of the modified Lommel functions with the Lommel function,…

Classical Analysis and ODEs · Mathematics 2017-04-18 Saiful R Mondal

In decision-dependent games, multiple players optimize their decisions under a data distribution that shifts with their joint actions, creating complex dynamics in applications like market pricing. A practical consequence of these dynamics…

Computer Science and Game Theory · Computer Science 2025-09-04 Guangzheng Zhong , Yang Liu , Jiming Liu