{"list":"other","total":59,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"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":"1812.07956","title":"On Lazy Training in Differentiable Programming","created":"2018-12-19","cited_by_count":675},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"1407.7722","title":"OpenML: networked science in machine learning","created":"2014-07-29","cited_by_count":526},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"2106.01342","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","created":"2021-06-02","cited_by_count":319},{"id":"1804.11271","title":"Gaussian Process Behaviour in Wide Deep Neural Networks","created":"2018-04-30","cited_by_count":317},{"id":"1411.4357","title":"Sketching as a Tool for Numerical Linear Algebra","created":"2014-11-17","cited_by_count":288},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"2006.03875","title":"Coresets via Bilevel Optimization for Continual Learning and Streaming","created":"2020-06-06","cited_by_count":192},{"id":"2010.15110","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel","created":"2020-10-28","cited_by_count":187},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151},{"id":"2111.00034","title":"Neural Networks as Kernel Learners: The Silent Alignment Effect","created":"2021-10-29","cited_by_count":106},{"id":"1901.05954","title":"Diverse mini-batch Active Learning","created":"2019-01-17","cited_by_count":89},{"id":"1906.01930","title":"Approximate Inference Turns Deep Networks into Gaussian Processes","created":"2019-06-05","cited_by_count":89},{"id":"2106.09675","title":"Gone Fishing: Neural Active Learning with Fisher Embeddings","created":"2021-06-17","cited_by_count":88},{"id":"1711.00941","title":"Deep Active Learning over the Long Tail","created":"2017-11-02","cited_by_count":84},{"id":"2101.11665","title":"On Statistical Bias In Active Learning: How and When To Fix It","created":"2021-01-27","cited_by_count":75},{"id":"1908.02144","title":"Bayesian Batch Active Learning as Sparse Subset Approximation","created":"2019-08-06","cited_by_count":68},{"id":"2112.03235","title":"Simulation Intelligence: Towards a New Generation of Scientific Methods","created":"2021-12-06","cited_by_count":68},{"id":"1906.07975","title":"Batch Active Learning Using Determinantal Point Processes","created":"2019-06-19","cited_by_count":43},{"id":"1805.04735","title":"Pool-Based Sequential Active Learning for Regression","created":"2018-05-12","cited_by_count":33},{"id":"2102.12567","title":"Sketching Curvature for Efficient Out-of-Distribution Detection for Deep Neural Networks","created":"2021-02-24","cited_by_count":32},{"id":"2106.07880","title":"Scaling Neural Tangent Kernels via Sketching and Random Features","created":"2021-06-15","cited_by_count":32},{"id":"2110.08611","title":"Deep Active Learning by Leveraging Training Dynamics","created":"2021-10-16","cited_by_count":32},{"id":"1912.08416","title":"Benchmarking the Neural Linear Model for Regression","created":"2019-12-18","cited_by_count":31},{"id":"2104.08312","title":"Data Shapley Valuation for Efficient Batch Active Learning","created":"2021-04-16","cited_by_count":27},{"id":"2105.10585","title":"Properties of the After Kernel","created":"2021-05-21","cited_by_count":27},{"id":"2105.14301","title":"A Theory of Neural Tangent Kernel Alignment and Its Influence on Training","created":"2021-05-29","cited_by_count":25},{"id":"2111.03577","title":"Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning","created":"2021-11-05","cited_by_count":25},{"id":"1806.09856","title":"Dropout-based Active Learning for Regression","created":"2018-06-26","cited_by_count":24},{"id":"2106.03243","title":"Neural Active Learning with Performance Guarantees","created":"2021-06-06","cited_by_count":22},{"id":"1811.03897","title":"Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensembles","created":"2018-11-09","cited_by_count":20},{"id":"2110.11875","title":"GeneDisco: A Benchmark for Experimental Design in Drug Discovery","created":"2021-10-22","cited_by_count":18},{"id":"2010.09654","title":"Semi-supervised Batch Active Learning via Bilevel Optimization","created":"2020-10-19","cited_by_count":16},{"id":"2009.12820","title":"Experimental Design for Overparameterized Learning with Application to Single Shot Deep Active Learning","created":"2020-09-27","cited_by_count":9},{"id":"2010.06890","title":"Identifying Wrongly Predicted Samples: A Method for Active Learning","created":"2020-10-14","cited_by_count":8},{"id":"2008.08400","title":"Improving predictions of Bayesian neural nets via local linearization","created":"2020-08-19","cited_by_count":7},{"id":"1812.11346","title":"Explaining Aggregates for Exploratory Analytics","created":"2018-12-29","cited_by_count":6},{"id":"2104.01351","title":"Random Features for the Neural Tangent Kernel","created":"2021-04-03","cited_by_count":6},{"id":"2011.02408","title":"Which Minimizer Does My Neural Network Converge To?","created":"2020-11-04","cited_by_count":4},{"id":"1507.01555","title":"Approximate Greedy Clustering and Distance Selection for Graph Metrics","created":"2015-07-06","cited_by_count":3}],"next_cursor":null}