{"total":41,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50,"area":null},{"id":"2306.04251","title":"Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks","created":"2023-06-07","cited_by_count":39,"area":null},{"id":"2210.01768","title":"Disentanglement with Biological Constraints: A Theory of Functional Cell Types","created":"2022-09-30","cited_by_count":30,"area":null},{"id":"2104.11044","title":"Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes","created":"2021-04-22","cited_by_count":28,"area":null},{"id":"2201.02115","title":"The dynamics of representation learning in shallow, non-linear autoencoders","created":"2022-01-06","cited_by_count":27,"area":null},{"id":"2301.08203","title":"An SDE for Modeling SAM: Theory and Insights","created":"2023-01-19","cited_by_count":22,"area":null},{"id":"2305.11041","title":"High-dimensional Asymptotics of Denoising Autoencoders","created":"2023-05-18","cited_by_count":19,"area":null},{"id":"2102.08373","title":"Analysis of feature learning in weight-tied autoencoders via the mean field lens","created":"2021-02-16","cited_by_count":14,"area":null},{"id":"2110.04825","title":"Deep Bayesian inference for seismic imaging with tasks","created":"2021-10-10","cited_by_count":12,"area":null},{"id":"2506.17093","title":"Identifiability of Deep Polynomial Neural Networks","created":"2025-06-20","cited_by_count":12,"area":null},{"id":"2102.11495","title":"Anytime Sampling for Autoregressive Models via Ordered Autoencoding","created":"2021-02-23","cited_by_count":11,"area":null},{"id":"2309.02028","title":"Non-Parametric Representation Learning with Kernels","created":"2023-09-05","cited_by_count":11,"area":null},{"id":"2505.11846","title":"Learning on a Razor's Edge: Identifiability and Singularity of Polynomial Neural Networks","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2401.07250","title":"Stabilizing Sharpness-aware Minimization Through A Simple Renormalization Strategy","created":"2024-01-14","cited_by_count":8,"area":null},{"id":"2302.02563","title":"Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2111.08706","title":"How and When Random Feedback Works: A Case Study of Low-Rank Matrix Factorization","created":"2021-11-17","cited_by_count":5,"area":null},{"id":"2402.05013","title":"Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth","created":"2024-02-07","cited_by_count":5,"area":null},{"id":"2307.08657","title":"Neural Image Compression: Generalization, Robustness, and Spectral Biases","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2510.01621","title":"Posterior Collapse as a Phase Transition in Variational Autoencoders","created":"2025-10-02","cited_by_count":4,"area":null},{"id":"2212.13468","title":"Fundamental Limits of Two-layer Autoencoders, and Achieving Them with Gradient Methods","created":"2022-12-27","cited_by_count":3,"area":null},{"id":"2309.02011","title":"Representation Learning Dynamics of Self-Supervised Models","created":"2023-09-05","cited_by_count":3,"area":null},{"id":"2206.05530","title":"Memorization-Dilation: Modeling Neural Collapse Under Label Noise","created":"2022-06-11","cited_by_count":2,"area":null},{"id":"2210.01760","title":"Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factors","created":"2022-10-04","cited_by_count":2,"area":null},{"id":"2308.03215","title":"The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning","created":"2023-08-06","cited_by_count":2,"area":null},{"id":"2310.20599","title":"Brain-like Flexible Visual Inference by Harnessing Feedback-Feedforward Alignment","created":"2023-10-31","cited_by_count":2,"area":null},{"id":"2506.20344","title":"A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2601.19179","title":"PCAE: Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2106.02796","title":"Principal Bit Analysis: Autoencoding with Schur-Concave Loss","created":"2021-06-05","cited_by_count":1,"area":null},{"id":"2212.01046","title":"Improved Representation Learning Through Tensorized Autoencoders","created":"2022-12-02","cited_by_count":1,"area":null},{"id":"2605.21324","title":"Stimulus symmetries can confound representational similarity analyses","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2202.08299","title":"The learning phases in NN: From Fitting the Majority to Fitting a Few","created":"2022-02-16","cited_by_count":0,"area":null},{"id":"2405.15895","title":"Manifold Metric: A Loss Landscape Approach for Predicting Model Performance","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2409.09361","title":"Beta-Sigma VAE: Separating beta and decoder variance in Gaussian variational autoencoder","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2509.18997","title":"Theoretical Foundations of Representation Learning using Unlabeled Data: Statistics and Optimization","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2605.09160","title":"Objective-Specific Privileged Bases via Full-Prefix Matryoshka Learning","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.28464","title":"Singular Learning and Occam's Razor in Deep Monomial Networks","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.25288","title":"When Does Deep Representation Learning Help Single-Cell Clustering? A Sensitivity-Aware Diagnostic Benchmark for Biomedical AI Pipelines","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.11876","title":"On the Regularization Landscape for the Linear Recommendation Models","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.20333","title":"Sharp Reconstruction Bounds for Autoencoders Using the Same Forward Map","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.03640","title":"Broken scale symmetries in undercomplete linear autoencoders","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}