{"total":24,"rows":[{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120,"area":null},{"id":"2111.01549","title":"Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima","created":"2021-10-30","cited_by_count":118,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"area":null},{"id":"2202.03038","title":"Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry","created":"2022-02-07","cited_by_count":28,"area":null},{"id":"2110.00683","title":"Learning through atypical \"phase transitions\" in overparameterized neural networks","created":"2021-10-01","cited_by_count":21,"area":null},{"id":"2208.13219","title":"Visualizing high-dimensional loss landscapes with Hessian directions","created":"2022-08-28","cited_by_count":16,"area":null},{"id":"2110.14583","title":"Deep learning via message passing algorithms based on belief propagation","created":"2021-10-27","cited_by_count":12,"area":null},{"id":"2403.02886","title":"Revisiting Confidence Estimation: Towards Reliable Failure Prediction","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2111.10192","title":"An Expectation-Maximization Perspective on Federated Learning","created":"2021-11-19","cited_by_count":9,"area":null},{"id":"2305.06435","title":"Phase transitions in the mini-batch size for sparse and dense two-layer neural networks","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2206.10915","title":"Understanding the effect of sparsity on neural networks robustness","created":"2022-06-22","cited_by_count":8,"area":null},{"id":"2203.05443","title":"Bias-variance decomposition of overparameterized regression with random linear features","created":"2022-03-10","cited_by_count":7,"area":null},{"id":"2310.05401","title":"Entropy-MCMC: Sampling from Flat Basins with Ease","created":"2023-10-09","cited_by_count":6,"area":null},{"id":"2402.19102","title":"FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution Robustness","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2307.04719","title":"On the curvature of the loss landscape","created":"2023-07-10","cited_by_count":3,"area":null},{"id":"2403.00230","title":"On Cyclical MCMC Sampling","created":"2024-03-01","cited_by_count":2,"area":null},{"id":"2503.10404","title":"Architecture-Aware Minimization (A$^2$M): How to Find Flat Minima in Neural Architecture Search","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2102.11210","title":"Non-Convex Optimization with Spectral Radius Regularization","created":"2021-02-22","cited_by_count":1,"area":null},{"id":"2505.10457","title":"SEAL: Searching Expandable Architectures for Incremental Learning","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2602.05849","title":"Visualizing the loss landscapes of physics-informed neural networks","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.15367","title":"Controlled Langevin Dynamics for Sampling of Feedforward Neural Networks Trained with Minibatches","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2210.04745","title":"Low-power multi-mode fiber projector overcomes shallow neural networks classifiers","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2602.21064","title":"Motivation is Something You Need","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2605.09256","title":"Improving Generalization by Permutation Routing Across Model Copies","created":"2026-05-10","cited_by_count":0,"area":null}],"next_cursor":null}