English
Related papers

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

200 papers

The learning objective plays a fundamental role to build a recommender system. Most methods routinely adopt either pointwise or pairwise loss to train the model parameters, while rarely pay attention to softmax loss due to its computational…

Information Retrieval · Computer Science 2023-12-20 Jiancan Wu , Xiang Wang , Xingyu Gao , Jiawei Chen , Hongcheng Fu , Tianyu Qiu

In this note we provide a full conjugacy and subdifferential calculus for convex convex-composite functions in finite-dimensional space. Our approach, based on infimal convolution and cone-convexity, is straightforward and yields the…

Optimization and Control · Mathematics 2019-08-22 James V. Burke , Tim Hoheisel , Quang V. Nguyen

Adversarial training, a special case of multi-objective optimization, is an increasingly prevalent machine learning technique: some of its most notable applications include GAN-based generative modeling and self-play techniques in…

Machine Learning · Statistics 2021-03-17 Gauthier Gidel , David Balduzzi , Wojciech Marian Czarnecki , Marta Garnelo , Yoram Bachrach

The Gumbel-Max trick is the basis of many relaxed gradient estimators. These estimators are easy to implement and low variance, but the goal of scaling them comprehensively to large combinatorial distributions is still outstanding. Working…

Machine Learning · Statistics 2021-03-02 Max B. Paulus , Dami Choi , Daniel Tarlow , Andreas Krause , Chris J. Maddison

Estimation of convex functions finds broad applications in engineering and science, while convex shape constraint gives rise to numerous challenges in asymptotic performance analysis. This paper is devoted to minimax optimal estimation of…

Statistics Theory · Mathematics 2013-06-11 Teresa M. Lebair , Jinglai Shen , Xiao Wang

Within convex analysis, a rich theory with various applications has been evolving since the proximal average of convex functions was first introduced over a decade ago. When one considers the subdifferential of the proximal average, a…

Optimization and Control · Mathematics 2015-05-12 Sedi Bartz , Heinz H. Bauschke , Sarah M. Moffat , Xianfu Wang

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly…

Machine Learning · Statistics 2017-11-21 Weiyang Liu , Yandong Wen , Zhiding Yu , Meng Yang

Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the…

Reward function, as an incentive representation that recognizes humans' agency and rationalizes humans' actions, is particularly appealing for modeling human behavior in human-robot interaction. Inverse Reinforcement Learning is an…

Artificial Intelligence · Computer Science 2021-03-09 Ran Tian , Masayoshi Tomizuka , Liting Sun

Softmax is widely used in neural networks for multiclass classification, gate structure and attention mechanisms. The statistical assumption that the input is normal distributed supports the gradient stability of Softmax. However, when used…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Shulun Wang , Bin Liu , Feng Liu

Deep convolutional neural networks (CNNs) trained with logistic and softmax losses have made significant advancement in visual recognition tasks in computer vision. When training data exhibit class imbalances, the class-wise reweighted…

Machine Learning · Computer Science 2020-03-06 Xiangrui Li , Xin Li , Deng Pan , Dongxiao Zhu

The Softmax loss is one of the most widely employed surrogate objectives for classification and ranking tasks. To elucidate its theoretical properties, the Fenchel-Young framework situates it as a canonical instance within a broad family of…

Machine Learning · Computer Science 2026-02-02 Yuanhao Pu , Defu Lian , Enhong Chen

We use gradient Young measures generated by Lipschitz maps to define a relaxation of integral functionals which are allowed to attain the value $+\infty$ and can model ideal locking in elasticity as defined by Prager in 1957. Furthermore,…

Analysis of PDEs · Mathematics 2018-06-01 Barbora Benešová , Martin Kružík , Anja Schlömerkemper

We propose an extended generalization of the pseudo Huber loss formulation. We show that using the log-exp transform together with the logistic function, we can create a loss which combines the desirable properties of the strictly convex…

Machine Learning · Statistics 2022-02-24 Kaan Gokcesu , Hakan Gokcesu

We investigate a class of reinforcement learning dynamics where players adjust their strategies based on their actions' cumulative payoffs over time - specifically, by playing mixed strategies that maximize their expected cumulative payoff…

Optimization and Control · Mathematics 2016-02-10 Panayotis Mertikopoulos , William H. Sandholm

We provide two characterizations, one axiomatic and the other neuro-computational, of the dependence of choice probabilities on deadlines, within the widely used softmax representation \[ p_{t}\left( a,A\right) =\dfrac{e^{\frac{u\left(…

Theoretical Economics · Economics 2021-01-28 Simone Cerreia-Vioglio , Fabio Maccheroni , Massimo Marinacci , Aldo Rustichini

This paper presents a tractable algorithm for estimating an unknown Lipschitz function from noisy observations and establishes an upper bound on its convergence rate. The approach extends max-affine methods from convex shape-restricted…

Machine Learning · Statistics 2025-11-20 Gábor Balázs

In this paper, we address stochastic optimization problems involving a composition of a non-smooth outer function and a smooth inner function, a formulation frequently encountered in machine learning and operations research. To deal with…

Optimization and Control · Mathematics 2026-05-15 Tommaso Giovannelli , Jingfu Tan , Luis Nunes Vicente

Building upon recent advances in entropy-regularized optimal transport, and upon Fenchel duality between measures and continuous functions , we propose a generalization of the logistic loss that incorporates a metric or cost between…

Machine Learning · Statistics 2019-05-16 Arthur Mensch , Mathieu Blondel , Gabriel Peyré

In this paper, we study some properties such as the monotonicity, logarithmically complete monotonicity, logarithmic convexity, and geometric convexity, of the combinations of gamma function and power function. The results we obtain…

Classical Analysis and ODEs · Mathematics 2022-05-26 Peipei Du , Gendi Wang
‹ Prev 1 3 4 5 6 7 10 Next ›