{"list":"other","total":69,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1907.10902","title":"Optuna: A Next-generation Hyperparameter Optimization Framework","created":"2019-07-25","cited_by_count":2501},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"2002.07394","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","created":"2020-02-18","cited_by_count":692},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1711.04623","title":"Three Factors Influencing Minima in SGD","created":"2017-11-13","cited_by_count":273},{"id":"2110.12088","title":"Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations","created":"2021-10-22","cited_by_count":256},{"id":"1702.03849","title":"Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis","created":"2017-02-13","cited_by_count":243},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129},{"id":"2205.09745","title":"Understanding Gradient Descent on Edge of Stability in Deep Learning","created":"2022-05-19","cited_by_count":128},{"id":"1512.07666","title":"Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks","created":"2015-12-23","cited_by_count":121},{"id":"2106.06530","title":"Label Noise SGD Provably Prefers Flat Global Minimizers","created":"2021-06-11","cited_by_count":121},{"id":"2203.04181","title":"Selective-Supervised Contrastive Learning with Noisy Labels","created":"2022-03-08","cited_by_count":112},{"id":"1707.06618","title":"Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization","created":"2017-07-20","cited_by_count":97},{"id":"2205.14083","title":"Sharpness-Aware Training for Free","created":"2022-05-27","cited_by_count":95},{"id":"2302.07011","title":"A Modern Look at the Relationship between Sharpness and Generalization","created":"2023-02-14","cited_by_count":92},{"id":"1902.00744","title":"Asymmetric Valleys: Beyond Sharp and Flat Local Minima","created":"2019-02-02","cited_by_count":90},{"id":"2012.04462","title":"Multi-Objective Interpolation Training for Robustness to Label Noise","created":"2020-12-08","cited_by_count":86},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53},{"id":"2210.01513","title":"The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima","created":"2022-10-04","cited_by_count":51},{"id":"2012.03801","title":"A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization","created":"2020-12-07","cited_by_count":44},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39},{"id":"2307.11007","title":"Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization","created":"2023-07-20","cited_by_count":39},{"id":"1910.02008","title":"Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimization","created":"2019-10-04","cited_by_count":38},{"id":"1808.07105","title":"Non-asymptotic bounds for sampling algorithms without log-concavity","created":"2018-08-21","cited_by_count":35},{"id":"2008.05367","title":"Non-convex Learning via Replica Exchange Stochastic Gradient MCMC","created":"2020-08-12","cited_by_count":34},{"id":"2203.03756","title":"Flat minima generalize for low-rank matrix recovery","created":"2022-03-07","cited_by_count":28},{"id":"2010.09800","title":"A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions","created":"2020-10-19","cited_by_count":26},{"id":"2311.13584","title":"On diffusion-based generative models and their error bounds: The log-concave case with full convergence estimates","created":"2023-11-22","cited_by_count":25},{"id":"2006.14514","title":"Taming neural networks with TUSLA: Non-convex learning via adaptive stochastic gradient Langevin algorithms","created":"2020-06-25","cited_by_count":21},{"id":"2405.03676","title":"Why is SAM Robust to Label Noise?","created":"2024-05-06","cited_by_count":21},{"id":"2501.12666","title":"Explicit Eigenvalue Regularization Improves Sharpness-Aware Minimization","created":"2025-01-22","cited_by_count":21},{"id":"2306.09850","title":"Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima","created":"2023-06-16","cited_by_count":20},{"id":"2203.16217","title":"Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization","created":"2022-03-30","cited_by_count":16},{"id":"2505.03432","title":"Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients","created":"2025-05-06","cited_by_count":15},{"id":"2102.04297","title":"Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise","created":"2021-02-08","cited_by_count":14},{"id":"2306.08553","title":"Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach","created":"2023-06-14","cited_by_count":14},{"id":"2401.08060","title":"Fundamental Convergence Analysis of Sharpness-Aware Minimization","created":"2024-01-16","cited_by_count":14},{"id":"2406.03682","title":"A Universal Class of Sharpness-Aware Minimization Algorithms","created":"2024-06-06","cited_by_count":14},{"id":"2305.15659","title":"How to escape sharp minima with random perturbations","created":"2023-05-25","cited_by_count":13},{"id":"2404.00357","title":"Revisiting Random Weight Perturbation for Efficiently Improving Generalization","created":"2024-03-30","cited_by_count":13},{"id":"2311.01046","title":"Time-Independent Information-Theoretic Generalization Bounds for SGLD","created":"2023-11-02","cited_by_count":12},{"id":"2001.08356","title":"Replica Exchange for Non-Convex Optimization","created":"2020-01-23","cited_by_count":11},{"id":"2105.13937","title":"Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks","created":"2021-05-28","cited_by_count":11},{"id":"2207.02600","title":"Non-asymptotic convergence bounds for modified tamed unadjusted Langevin algorithm in non-convex setting","created":"2022-07-06","cited_by_count":10},{"id":"2302.02713","title":"Flat Seeking Bayesian Neural Networks","created":"2023-02-06","cited_by_count":10},{"id":"2503.02225","title":"Sharpness-Aware Minimization: General Analysis and Improved Rates","created":"2025-03-04","cited_by_count":10},{"id":"2202.09867","title":"Interacting Contour Stochastic Gradient Langevin Dynamics","created":"2022-02-20","cited_by_count":9},{"id":"2401.07250","title":"Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy","created":"2024-01-14","cited_by_count":8},{"id":"1705.05640","title":"WebVision Challenge: Visual Learning and Understanding With Web Data","created":"2017-05-16","cited_by_count":7},{"id":"2102.06759","title":"Stochastic Gradient Langevin Dynamics with Variance Reduction","created":"2021-02-12","cited_by_count":7},{"id":"2304.01335","title":"Charting the Topography of the Neural Network Landscape with Thermal-Like Noise","created":"2023-04-03","cited_by_count":6},{"id":"2310.05401","title":"Entropy-MCMC: Sampling from Flat Basins with Ease","created":"2023-10-09","cited_by_count":6},{"id":"2410.22656","title":"Tilted Sharpness-Aware Minimization","created":"2024-10-30","cited_by_count":6},{"id":"2506.05454","title":"Zeroth-Order Optimization Finds Flat Minima","created":"2025-06-05","cited_by_count":6},{"id":"2210.13193","title":"Langevin dynamics based algorithm e-TH$\\varepsilon$O POULA for stochastic optimization problems with discontinuous stochastic gradient","created":"2022-10-24","cited_by_count":5},{"id":"2407.12993","title":"Improving SAM Requires Rethinking its Optimization Formulation","created":"2024-07-17","cited_by_count":4},{"id":"2410.16401","title":"Simplicity Bias via Global Convergence of Sharpness Minimization","created":"2024-10-21","cited_by_count":4},{"id":"2406.15664","title":"Flat Posterior Does Matter For Bayesian Model Averaging","created":"2024-06-21","cited_by_count":1}],"next_cursor":null}