conftrace_

logistic loss

30 papers

Explore in graph

Co-occurring keywords

gradient descent (1144) linear classifier (120) generalization bound (652) convergence rate (607) convex optimization (1321) exponential loss (10) convex loss function (19) empirical risk minimization (352) binary classification (678) weak learnability (3)

Papers

Classification with Deep Neural Networks and Logistic Loss JMLR 2024
The Space Complexity of Approximating Logistic Loss NIPS 2024
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization NIPS 2024
Discovering Preference Optimization Algorithms with and for Large Language Models NIPS 2024
Learning with Fitzpatrick Losses NIPS 2024
Online Structured Prediction with Fenchel–Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss COLT 2024
Structured Prediction with Stronger Consistency Guarantees NIPS 2023
Fast Sparse Classification for Generalized Linear and Additive Models AISTATS 2022
Self-training Converts Weak Learners to Strong Learners in Mixture Models AISTATS 2022
On the interplay between data structure and loss function in classification problems NIPS 2021
Coresets for Classification – Simplified and Strengthened NIPS 2021
Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime JMLR 2021
When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? JMLR 2021
When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT 2021
Early-stopped neural networks are consistent NIPS 2021
Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss COLT 2020
Robust high dimensional learning for Lipschitz and convex losses JMLR 2020
On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks AAAI 2020
Robust Bi-Tempered Logistic Loss Based on Bregman Divergences NIPS 2019
Geometric Losses for Distributional Learning ICML 2019
Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate AISTATS 2019
Convergence of Gradient Descent on Separable Data AISTATS 2019
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss NIPS 2018
Linking losses for density ratio and class-probability estimation ICML 2016
On Regularizing Rademacher Observation Losses NIPS 2016