{"total":38,"rows":[{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154,"area":null},{"id":"2105.03361","title":"What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory","created":"2021-05-07","cited_by_count":60,"area":null},{"id":"2201.12760","title":"Implicit Regularization Towards Rank Minimization in ReLU Networks","created":"2022-01-30","cited_by_count":53,"area":null},{"id":"2107.02561","title":"Rethinking Positional Encoding","created":"2021-07-06","cited_by_count":37,"area":null},{"id":"2207.11347","title":"An Impartial Take to the CNN vs Transformer Robustness Contest","created":"2022-07-22","cited_by_count":34,"area":null},{"id":"2107.04835","title":"Noise Stability Regularization for Improving BERT Fine-tuning","created":"2021-07-10","cited_by_count":29,"area":null},{"id":"2206.14502","title":"RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness","created":"2022-06-29","cited_by_count":27,"area":null},{"id":"2301.09554","title":"Deep Learning Meets Sparse Regularization: A Signal Processing Perspective","created":"2023-01-23","cited_by_count":21,"area":null},{"id":"2312.00359","title":"Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training","created":"2023-12-01","cited_by_count":20,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2506.06280","title":"Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias","created":"2025-06-06","cited_by_count":10,"area":null},{"id":"2106.08601","title":"Self-Supervised GANs with Label Augmentation","created":"2021-06-16","cited_by_count":9,"area":null},{"id":"2211.13771","title":"Towards Practical Control of Singular Values of Convolutional Layers","created":"2022-11-24","cited_by_count":9,"area":null},{"id":"2406.19049","title":"Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2501.07930","title":"An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2512.14366","title":"Optimizing Rank for High-Fidelity Implicit Neural Representations","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2103.04217","title":"Spectral Tensor Train Parameterization of Deep Learning Layers","created":"2021-03-07","cited_by_count":6,"area":null},{"id":"2112.08950","title":"Stable Long-Term Recurrent Video Super-Resolution","created":"2021-12-16","cited_by_count":6,"area":null},{"id":"2402.18863","title":"Probabilistic Lipschitzness and the Stable Rank for Comparing Explanation Models","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2110.02333","title":"On the Impact of Stable Ranks in Deep Nets","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2211.10558","title":"Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds","created":"2022-11-19","cited_by_count":3,"area":null},{"id":"2507.00327","title":"Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2603.18017","title":"Frayed RoPE and Long Inputs: A Geometric Perspective","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2606.19491","title":"Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2204.12466","title":"Meta-free few-shot learning via representation learning with weight averaging","created":"2022-04-26","cited_by_count":2,"area":null},{"id":"2510.04202","title":"Spectral Alignment as Predictor of Loss Explosion in Neural Network Training","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2111.15179","title":"A Highly Effective Low-Rank Compression of Deep Neural Networks with Modified Beam-Search and Modified Stable Rank","created":"2021-11-30","cited_by_count":1,"area":null},{"id":"2301.09820","title":"A Stability Analysis of Fine-Tuning a Pre-Trained Model","created":"2023-01-24","cited_by_count":1,"area":null},{"id":"2602.01734","title":"MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2604.02830","title":"GRADE: Probing Knowledge Gaps in LLMs through Gradient Subspace Dynamics","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.11142","title":"Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2403.15832","title":"Time-series Initialization and Conditioning for Video-agnostic Stabilization of Video Super-Resolution using Recurrent Networks","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2410.21656","title":"Dimensionality-induced information loss of outliers in deep neural networks","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2603.02806","title":"The Price of Robustness: Stable Classifiers Need Overparameterization","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2605.28975","title":"A Training-Time Diagnostic for Generalization via the Log-Alignment Ratio","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2610.09709","title":"Pretraining Shapes Spectral Structure: Architecture- and Strategy-Conditional Prediction of OOD Robustness in Foundation Models","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}