{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"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":"1312.6211","title":"An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks","created":"2013-12-21","cited_by_count":722},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1804.06561","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","created":"2018-04-18","cited_by_count":466},{"id":"1910.07104","title":"Orthogonal Gradient Descent for Continual Learning","created":"2019-10-15","cited_by_count":369},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1812.05720","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","created":"2018-12-13","cited_by_count":323},{"id":"1902.03932","title":"Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning","created":"2019-02-11","cited_by_count":203},{"id":"2011.14522","title":"Feature Learning in Infinite-Width Neural Networks","created":"2020-11-30","cited_by_count":190},{"id":"2007.15801","title":"Finite Versus Infinite Neural Networks: an Empirical Study","created":"2020-07-31","cited_by_count":157},{"id":"1912.02803","title":"Neural Tangents: Fast and Easy Infinite Neural Networks in Python","created":"2019-12-05","cited_by_count":149},{"id":"2010.00827","title":"Neural Thompson Sampling","created":"2020-10-02","cited_by_count":128},{"id":"2104.00405","title":"Avalanche: an End-to-End Library for Continual Learning","created":"2021-04-01","cited_by_count":124},{"id":"1903.09588","title":"Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence","created":"2019-03-22","cited_by_count":122},{"id":"2007.01547","title":"Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers","created":"2020-07-03","cited_by_count":119},{"id":"2104.04975","title":"Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning","created":"2021-04-11","cited_by_count":106},{"id":"2010.04003","title":"A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix","created":"2020-10-07","cited_by_count":103},{"id":"1909.08156","title":"Dynamics of Deep Neural Networks and Neural Tangent Hierarchy","created":"2019-09-18","cited_by_count":96},{"id":"1906.01930","title":"Approximate Inference Turns Deep Networks into Gaussian Processes","created":"2019-06-05","cited_by_count":89},{"id":"2205.09588","title":"How catastrophic can catastrophic forgetting be in linear regression?","created":"2022-05-19","cited_by_count":81},{"id":"1905.10961","title":"Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks","created":"2019-05-27","cited_by_count":76},{"id":"2006.11942","title":"Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent","created":"2020-06-21","cited_by_count":68},{"id":"2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","created":"2021-10-21","cited_by_count":64},{"id":"2105.03703","title":"Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics","created":"2021-05-08","cited_by_count":57},{"id":"2305.20028","title":"A Study of Bayesian Neural Network Surrogates for Bayesian Optimization","created":"2023-05-31","cited_by_count":50},{"id":"2107.03144","title":"Neural Contextual Bandits without Regret","created":"2021-07-07","cited_by_count":40},{"id":"2008.11245","title":"Deep Networks and the Multiple Manifold Problem","created":"2020-08-25","cited_by_count":35},{"id":"2306.03534","title":"Continual Learning in Linear Classification on Separable Data","created":"2023-06-06","cited_by_count":34},{"id":"2207.06475","title":"Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized Regime","created":"2022-06-01","cited_by_count":29},{"id":"2106.06615","title":"Precise characterization of the prior predictive distribution of deep ReLU networks","created":"2021-06-11","cited_by_count":28},{"id":"2111.13807","title":"Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization","created":"2021-11-27","cited_by_count":25},{"id":"2202.11670","title":"Wide Mean-Field Bayesian Neural Networks Ignore the Data","created":"2022-02-23","cited_by_count":22},{"id":"1910.00359","title":"Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory","created":"2019-10-01","cited_by_count":21},{"id":"2106.06529","title":"The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective","created":"2021-06-11","cited_by_count":21},{"id":"2302.07384","title":"The Geometry of Neural Nets' Parameter Spaces Under Reparametrization","created":"2023-02-14","cited_by_count":16},{"id":"2106.10065","title":"Being a Bit Frequentist Improves Bayesian Neural Networks","created":"2021-06-18","cited_by_count":15},{"id":"2205.10041","title":"Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks","created":"2022-05-20","cited_by_count":14},{"id":"2206.02927","title":"Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime","created":"2022-06-06","cited_by_count":11},{"id":"2304.08309","title":"Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization","created":"2023-04-17","cited_by_count":10},{"id":"2201.04738","title":"Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks","created":"2022-01-12","cited_by_count":9}],"next_cursor":null}