English
Related papers

Related papers: On the Universality of the Logistic Loss Function

200 papers

The LogSumExp function, dual to the Kullback-Leibler (KL) divergence, plays a central role in many important optimization problems, including entropy-regularized optimal transport (OT) and distributionally robust optimization (DRO). In…

Optimization and Control · Mathematics 2026-02-04 Egor Gladin , Alexey Kroshnin , Jia-Jie Zhu , Pavel Dvurechensky

Kullback--Leibler (KL) divergence is a fundamental measure of the dissimilarity between two probability distributions, but it can become unstable in high-dimensional settings due to its sensitivity to mismatches in distributional support.…

Information Theory · Computer Science 2025-02-03 Yifeng Peng , Dantong Li , Xinyi Li , Zhiding Liang , Yongshan Ding , Ying Wang

In binary classification and regression problems, it is well understood that Lipschitz continuity and smoothness of the loss function play key roles in governing generalization error bounds for empirical risk minimization algorithms. In…

Machine Learning · Computer Science 2016-09-14 Ambuj Tewari , Sougata Chaudhuri

This work proposes a new loss function targeting classification problems, utilizing a source of information overlooked by cross entropy loss. First, we derive a series of the tightest upper and lower bounds for the probability of a random…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Ali Ghobadzadeh , Amir Lashkari

In this paper, some new upper bounds for Kullback-Leibler divergence(KL-divergence) based on $L^1, L^2$ and $L^\infty$ norms of density functions are discussed. Our findings unveil that the convergence in KL-divergence sense sandwiches…

Probability · Mathematics 2024-10-31 Liuquan Yao , Songhao Liu

Model calibration is essential for ensuring that the predictions of deep neural networks accurately reflect true probabilities in real-world classification tasks. However, deep networks often produce over-confident or under-confident…

Machine Learning · Computer Science 2025-04-01 Jinxu Lin , Linwei Tao , Minjing Dong , Chang Xu

The Kullback-Leibler divergence, the Kullback-Leibler variation, and the Bernstein "norm" are used to quantify discrepancies among probability distributions in likelihood models such as nonparametric maximum likelihood and nonparametric…

Statistics Theory · Mathematics 2026-01-27 Tetsuya Kaji

We introduce a tunable loss function called $\alpha$-loss, parameterized by $\alpha \in (0,\infty]$, which interpolates between the exponential loss ($\alpha = 1/2$), the log-loss ($\alpha = 1$), and the 0-1 loss ($\alpha = \infty$), for…

Machine Learning · Computer Science 2022-12-22 Tyler Sypherd , Mario Diaz , John Kevin Cava , Gautam Dasarathy , Peter Kairouz , Lalitha Sankar

In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of (1) a weighted Mean Square Error (wMSE)…

Machine Learning · Computer Science 2025-03-12 Jiequan Cui , Beier Zhu , Qingshan Xu , Zhuotao Tian , Xiaojuan Qi , Bei Yu , Hanwang Zhang , Richang Hong

The logistic loss function is often advocated in machine learning and statistics as a smooth and strictly convex surrogate for the 0-1 loss. In this paper we investigate the question of whether these smoothness and convexity properties make…

Machine Learning · Computer Science 2014-05-16 Elad Hazan , Tomer Koren , Kfir Y. Levy

We study the loss surface of a feed-forward neural network with ReLU non-linearities, regularized with weight decay. We show that the regularized loss function is piecewise strongly convex on an important open set which contains, under some…

Neural and Evolutionary Computing · Computer Science 2019-12-10 Tristan Milne

Blasiok (SODA'18) recently introduced the notion of a subgaussian sampler, defined as an averaging sampler for approximating the mean of functions $f:\{0,1\}^m \to \mathbb{R}$ such that $f(U_m)$ has subgaussian tails, and asked for explicit…

Computational Complexity · Computer Science 2019-09-19 Rohit Agrawal

The generalized Kullback-Leibler divergence (K-Ld) in Tsallis statistics [constrained by the additive duality of generalized statistics (dual generalized K-Ld)] is here reconciled with the theory of Bregman divergences for expectations…

Statistical Mechanics · Physics 2015-05-27 R. C. Venkatesan , A. Plastino

Elicitable functionals and (strictly) consistent scoring functions are of interest due to their utility of determining (uniquely) optimal forecasts, and thus the ability to effectively backtest predictions. However, in practice, assuming…

Methodology · Statistics 2026-03-18 Kathleen E. Miao , Silvana M. Pesenti

In binary classification problems, mainly two approaches have been proposed; one is loss function approach and the other is uncertainty set approach. The loss function approach is applied to major learning algorithms such as support vector…

Machine Learning · Statistics 2012-05-01 Takafumi Kanamori , Akiko Takeda , Taiji Suzuki

Consider the nonparametric logistic regression problem. In the logistic regression, we usually consider the maximum likelihood estimator, and the excess risk is the expectation of the Kullback-Leibler (KL) divergence between the true and…

Statistics Theory · Mathematics 2025-02-26 Atsutomo Yara , Yoshikazu Terada

The Huber loss is a robust loss function used for a wide range of regression tasks. To utilize the Huber loss, a parameter that controls the transitions from a quadratic function to an absolute value function needs to be selected. We…

Machine Learning · Statistics 2020-11-20 Gregory P. Meyer

Estimating Kullback Leibler (KL) divergence from samples of two distributions is essential in many machine learning problems. Variational methods using neural network discriminator have been proposed to achieve this task in a scalable…

Machine Learning · Computer Science 2021-10-01 Sandesh Ghimire , Aria Masoomi , Jennifer Dy

To characterize the Kullback-Leibler divergence and Fisher information in general parametrized hidden Markov models, in this paper, we first show that the log likelihood and its derivatives can be represented as an additive functional of a…

Statistics Theory · Mathematics 2023-03-15 Cheng-Der Fuh , Chu-Lan Michael Kao , Tianxiao Pang

When model predictions inform downstream decision making, a natural question is under what conditions can the decision-makers simply respond to the predictions as if they were the true outcomes. Calibration suffices to guarantee that simple…

Machine Learning · Computer Science 2025-04-23 Jingwu Tang , Jiayun Wu , Zhiwei Steven Wu , Jiahao Zhang