{"total":89,"rows":[{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2205.11506","title":"Orchestra: Unsupervised Federated Learning via Globally Consistent Clustering","created":"2022-05-23","cited_by_count":45,"area":null},{"id":"2302.06232","title":"Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data","created":"2023-02-13","cited_by_count":43,"area":null},{"id":"2211.14699","title":"A Theoretical Study of Inductive Biases in Contrastive Learning","created":"2022-11-27","cited_by_count":40,"area":null},{"id":"2302.02774","title":"The SSL Interplay: Augmentations, Inductive Bias, and Generalization","created":"2023-02-06","cited_by_count":40,"area":null},{"id":"2407.00143","title":"InfoNCE: Identifying the Gap Between Theory and Practice","created":"2024-06-28","cited_by_count":40,"area":null},{"id":"2205.01789","title":"Do More Negative Samples Necessarily Hurt in Contrastive Learning?","created":"2022-05-03","cited_by_count":39,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38,"area":null},{"id":"2404.03827","title":"Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models","created":"2024-04-04","cited_by_count":38,"area":null},{"id":"2302.07920","title":"InfoNCE Loss Provably Learns Cluster-Preserving Representations","created":"2023-02-15","cited_by_count":37,"area":null},{"id":"2303.15438","title":"On the Stepwise Nature of Self-Supervised Learning","created":"2023-03-27","cited_by_count":36,"area":null},{"id":"2209.06235","title":"Improving Self-Supervised Learning by Characterizing Idealized Representations","created":"2022-09-13","cited_by_count":34,"area":null},{"id":"2210.01883","title":"Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions","created":"2022-10-04","cited_by_count":32,"area":null},{"id":"2305.16536","title":"Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression","created":"2023-05-25","cited_by_count":30,"area":null},{"id":"2306.04272","title":"On the Generalization of Multi-modal Contrastive Learning","created":"2023-06-07","cited_by_count":30,"area":null},{"id":"2205.14814","title":"Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding","created":"2022-05-30","cited_by_count":28,"area":null},{"id":"2303.00106","title":"The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning","created":"2023-02-28","cited_by_count":27,"area":null},{"id":"2310.00927","title":"Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP","created":"2023-10-02","cited_by_count":26,"area":null},{"id":"2302.12383","title":"Generalization Analysis for Contrastive Representation Learning","created":"2023-02-24","cited_by_count":25,"area":null},{"id":"2303.01566","title":"On the Provable Advantage of Unsupervised Pretraining","created":"2023-03-02","cited_by_count":22,"area":null},{"id":"2309.12559","title":"Invariant Learning via Probability of Sufficient and Necessary Causes","created":"2023-09-22","cited_by_count":22,"area":null},{"id":"2305.17326","title":"Matrix Information Theory for Self-Supervised Learning","created":"2023-05-27","cited_by_count":21,"area":null},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2306.00788","title":"Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2403.11391","title":"Investigating the Benefits of Projection Head for Representation Learning","created":"2024-03-18","cited_by_count":20,"area":null},{"id":"2206.01342","title":"Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2210.00638","title":"What shapes the loss landscape of self-supervised learning?","created":"2022-10-02","cited_by_count":19,"area":null},{"id":"2309.17281","title":"Information Flow in Self-Supervised Learning","created":"2023-09-29","cited_by_count":16,"area":null},{"id":"2406.09294","title":"You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning","created":"2024-06-13","cited_by_count":16,"area":null},{"id":"2312.00379","title":"Optimal Sample Complexity of Contrastive Learning","created":"2023-12-01","cited_by_count":15,"area":null},{"id":"2310.18904","title":"Identifiable Contrastive Learning with Automatic Feature Importance Discovery","created":"2023-10-29","cited_by_count":14,"area":null},{"id":"2210.14019","title":"The Curious Case of Benign Memorization","created":"2022-10-25","cited_by_count":12,"area":null},{"id":"2206.01646","title":"Integrating Prior Knowledge in Contrastive Learning with Kernel","created":"2022-06-03","cited_by_count":11,"area":null},{"id":"2503.00507","title":"Projection Head is Secretly an Information Bottleneck","created":"2025-03-01","cited_by_count":11,"area":null},{"id":"2402.05913","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2502.09252","title":"On the Importance of Embedding Norms in Self-Supervised Learning","created":"2025-02-13","cited_by_count":9,"area":null},{"id":"2502.09863","title":"Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models","created":"2025-02-14","cited_by_count":8,"area":null},{"id":"2208.02810","title":"Analyzing Data-Centric Properties for Graph Contrastive Learning","created":"2022-08-04","cited_by_count":7,"area":null},{"id":"2301.11915","title":"Understanding Self-Supervised Pretraining with Part-Aware Representation Learning","created":"2023-01-27","cited_by_count":7,"area":null},{"id":"2304.11718","title":"No Free Lunch in Self Supervised Representation Learning","created":"2023-04-23","cited_by_count":7,"area":null},{"id":"2311.02687","title":"Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning","created":"2023-11-05","cited_by_count":7,"area":null},{"id":"2406.00535","title":"Causal Contrastive Learning for Counterfactual Regression Over Time","created":"2024-06-01","cited_by_count":7,"area":null},{"id":"2406.16468","title":"The Hidden Pitfalls of the Cosine Similarity Loss","created":"2024-06-24","cited_by_count":7,"area":null},{"id":"2410.04959","title":"Collapse-Proof Non-Contrastive Self-Supervised Learning","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2411.06508","title":"Understanding the Role of Equivariance in Self-supervised Learning","created":"2024-11-10","cited_by_count":7,"area":null},{"id":"2212.13425","title":"GEDI: GEnerative and DIscriminative Training for Self-Supervised Learning","created":"2022-12-27","cited_by_count":6,"area":null},{"id":"2302.03068","title":"Evaluating Self-Supervised Learning via Risk Decomposition","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2306.03335","title":"Unraveling Projection Heads in Contrastive Learning: Insights from Expansion and Shrinkage","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2402.12613","title":"Analysis of Using Sigmoid Loss for Contrastive Learning","created":"2024-02-20","cited_by_count":6,"area":null},{"id":"2411.03517","title":"Understanding Self-Supervised Learning via Gaussian Mixture Models","created":"2024-11-05","cited_by_count":6,"area":null},{"id":"2502.20141","title":"Your contrastive learning problem is secretly a distribution alignment problem","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2503.24182","title":"CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization","created":"2025-03-31","cited_by_count":6,"area":null},{"id":"2301.12189","title":"Deciphering the Projection Head: Representation Evaluation Self-supervised Learning","created":"2023-01-28","cited_by_count":5,"area":null},{"id":"2312.03318","title":"Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift","created":"2023-12-06","cited_by_count":5,"area":null},{"id":"2402.01399","title":"A Probabilistic Model Behind Self-Supervised Learning","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2404.08701","title":"Can Contrastive Learning Refine Embeddings","created":"2024-04-11","cited_by_count":5,"area":null},{"id":"2506.04411","title":"Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2211.03162","title":"ProtoX: Explaining a Reinforcement Learning Agent via Prototyping","created":"2022-11-06","cited_by_count":4,"area":null},{"id":"2307.08913","title":"Towards the Sparseness of Projection Head in Self-Supervised Learning","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2310.04971","title":"Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift","created":"2023-10-08","cited_by_count":4,"area":null},{"id":"2411.01767","title":"A Theoretical Characterization of Optimal Data Augmentations in Self-Supervised Learning","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2511.12278","title":"PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning","created":"2025-11-15","cited_by_count":4,"area":null},{"id":"2310.03977","title":"Perfect Alignment May be Poisonous to Graph Contrastive Learning","created":"2023-10-06","cited_by_count":3,"area":null},{"id":"2603.03530","title":"Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning","created":"2026-03-03","cited_by_count":3,"area":null},{"id":"2308.15704","title":"Towards a Rigorous Analysis of Mutual Information in Contrastive Learning","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2401.00873","title":"Unifying Self-Supervised Clustering and Energy-Based Models","created":"2023-12-30","cited_by_count":2,"area":null},{"id":"2510.08852","title":"On the Alignment Between Supervised and Self-Supervised Contrastive Learning","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2601.19597","title":"The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-modal Divergence","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2606.07770","title":"Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2305.10229","title":"How does Contrastive Learning Organize Images?","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2310.11281","title":"Self-supervision meets kernel graph neural models: From architecture to augmentations","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2402.13465","title":"Unsupervised learning based object detection using Contrastive Learning","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2405.03355","title":"A Generalization Theory of Cross-Modality Distillation with Contrastive Learning","created":"2024-05-06","cited_by_count":1,"area":null},{"id":"2503.07214","title":"Cross-Lingual IPA Contrastive Learning for Zero-Shot NER","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2507.11161","title":"How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2509.16898","title":"The Complexity of Finding Local Optima in Contrastive Learning","created":"2025-09-21","cited_by_count":1,"area":null},{"id":"2605.03346","title":"Provable Accuracy Collapse in Embedding-Based Representations under Dimensionality Mismatch","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2310.19041","title":"On Linear Separation Capacity of Self-Supervised Representation Learning","created":"2023-10-29","cited_by_count":0,"area":null},{"id":"2312.02124","title":"VerA: Versatile Anonymization Applicable to Clinical Facial Photographs","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2401.15248","title":"Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective","created":"2024-01-26","cited_by_count":0,"area":null},{"id":"2504.10850","title":"How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2510.22655","title":"Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2510.24672","title":"Eigenfunction Extraction for Ordered Representation Learning","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2605.13943","title":"A Unified Geometric Framework for Weighted Contrastive Learning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.23504","title":"VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2607.07470","title":"A Theory of Contrastive Learning with Natural Images","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2609.38393","title":"Which Tasks Survive Self-Supervised Learning?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38834","title":"Optimal VC Dimension of Contrastive Learning with Margin","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}