{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1708.04552","title":"Improved Regularization of Convolutional Neural Networks with Cutout","created":"2017-08-15","cited_by_count":1628},{"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":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1902.06720","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","created":"2019-02-18","cited_by_count":738},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"1811.03804","title":"Gradient Descent Finds Global Minima of Deep Neural Networks","created":"2018-11-09","cited_by_count":574},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1901.08584","title":"Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks","created":"2019-01-24","cited_by_count":566},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"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":"1902.09229","title":"A Theoretical Analysis of Contrastive Unsupervised Representation Learning","created":"2019-02-25","cited_by_count":530},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"2110.09348","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","created":"2021-10-18","cited_by_count":378},{"id":"1811.04918","title":"Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers","created":"2018-11-12","cited_by_count":340},{"id":"1707.09564","title":"A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks","created":"2017-07-29","cited_by_count":314},{"id":"2106.04156","title":"Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss","created":"2021-06-08","cited_by_count":313},{"id":"1802.05296","title":"Stronger generalization bounds for deep nets via a compression approach","created":"2018-02-14","cited_by_count":307},{"id":"2102.06810","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","created":"2021-02-12","cited_by_count":256},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"2008.01064","title":"Predicting What You Already Know Helps: Provable Self-Supervised Learning","created":"2020-08-03","cited_by_count":152},{"id":"2008.10150","title":"Contrastive learning, multi-view redundancy, and linear models","created":"2020-08-24","cited_by_count":146},{"id":"2006.08558","title":"Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction","created":"2020-06-15","cited_by_count":142},{"id":"1705.09886","title":"Convergence Analysis of Two-layer Neural Networks with ReLU Activation","created":"2017-05-28","cited_by_count":137},{"id":"1804.05862","title":"Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach","created":"2018-04-16","cited_by_count":126},{"id":"2110.05025","title":"Self-supervised Learning is More Robust to Dataset Imbalance","created":"2021-10-11","cited_by_count":123},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119},{"id":"2202.08005","title":"Should You Mask 15% in Masked Language Modeling?","created":"2022-02-16","cited_by_count":118},{"id":"1803.06084","title":"A Kernel Theory of Modern Data Augmentation","created":"2018-03-16","cited_by_count":106},{"id":"2203.13457","title":"Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap","created":"2022-03-25","cited_by_count":105},{"id":"1803.01206","title":"On the Power of Over-parametrization in Neural Networks with Quadratic Activation","created":"2018-03-03","cited_by_count":102},{"id":"2111.00743","title":"Towards the Generalization of Contrastive Self-Supervised Learning","created":"2021-11-01","cited_by_count":99},{"id":"2202.14037","title":"Understanding Contrastive Learning Requires Incorporating Inductive Biases","created":"2022-02-28","cited_by_count":96},{"id":"2105.10446","title":"ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction","created":"2021-05-21","cited_by_count":84},{"id":"2106.09226","title":"Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning","created":"2021-06-17","cited_by_count":82},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76},{"id":"2204.00570","title":"Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation","created":"2022-04-01","cited_by_count":67},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63},{"id":"2003.02234","title":"Contrastive estimation reveals topic posterior information to linear models","created":"2020-03-04","cited_by_count":54},{"id":"1905.13344","title":"Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience","created":"2019-05-30","cited_by_count":51},{"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":"2207.04630","title":"On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence","created":"2022-07-11","cited_by_count":50},{"id":"1912.04265","title":"In Defense of Uniform Convergence: Generalization via derandomization with an application to interpolating predictors","created":"2019-12-09","cited_by_count":44},{"id":"2204.02683","title":"Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations","created":"2022-04-06","cited_by_count":44},{"id":"2211.14699","title":"A Theoretical Study of Inductive Biases in Contrastive Learning","created":"2022-11-27","cited_by_count":40},{"id":"2302.02774","title":"The SSL Interplay: Augmentations, Inductive Bias, and Generalization","created":"2023-02-06","cited_by_count":40},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","cited_by_count":38},{"id":"1908.07380","title":"PAC-Bayes with Backprop","created":"2019-08-19","cited_by_count":36},{"id":"2210.01883","title":"Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions","created":"2022-10-04","cited_by_count":32},{"id":"2203.15702","title":"Contrasting the landscape of contrastive and non-contrastive learning","created":"2022-03-29","cited_by_count":24},{"id":"2303.04435","title":"A Message Passing Perspective on Learning Dynamics of Contrastive Learning","created":"2023-03-08","cited_by_count":22},{"id":"2111.06636","title":"Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction","created":"2021-11-12","cited_by_count":17},{"id":"2010.11356","title":"Beyond Lazy Training for Over-parameterized Tensor Decomposition","created":"2020-10-22","cited_by_count":15},{"id":"1506.02544","title":"Learning with Group Invariant Features: A Kernel Perspective","created":"2015-06-08","cited_by_count":13},{"id":"1612.01988","title":"Local Group Invariant Representations via Orbit Embeddings","created":"2016-12-06","cited_by_count":12},{"id":"2210.16525","title":"Spectral Representation Learning for Conditional Moment Models","created":"2022-10-29","cited_by_count":12},{"id":"2202.09305","title":"Masked prediction tasks: a parameter identifiability view","created":"2022-02-18","cited_by_count":4}],"next_cursor":null}