{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1804.04235","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","created":"2018-04-11","cited_by_count":905},{"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":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1904.03758","title":"Meta-Learning with Differentiable Convex Optimization","created":"2019-04-07","cited_by_count":461},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1805.08136","title":"Meta-learning with differentiable closed-form solvers","created":"2018-05-21","cited_by_count":397},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"1312.3005","title":"One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling","created":"2013-12-11","cited_by_count":308},{"id":"1810.03548","title":"Meta-Learning: A Survey","created":"2018-10-08","cited_by_count":256},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"1611.01232","title":"Deep Information Propagation","created":"2016-11-04","cited_by_count":195},{"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":"1801.08930","title":"Recasting Gradient-Based Meta-Learning as Hierarchical Bayes","created":"2018-01-26","cited_by_count":180},{"id":"2007.01547","title":"Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers","created":"2020-07-03","cited_by_count":119},{"id":"1703.04782","title":"Online Learning Rate Adaptation with Hypergradient Descent","created":"2017-03-14","cited_by_count":118},{"id":"1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","created":"2019-07-09","cited_by_count":117},{"id":"1703.04813","title":"Learned Optimizers that Scale and Generalize","created":"2017-03-14","cited_by_count":110},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"id":"1712.08969","title":"Mean Field Residual Networks: On the Edge of Chaos","created":"2017-12-24","cited_by_count":83},{"id":"1812.07671","title":"Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL","created":"2018-12-18","cited_by_count":81},{"id":"1803.02021","title":"Understanding Short-Horizon Bias in Stochastic Meta-Optimization","created":"2018-03-06","cited_by_count":69},{"id":"1906.04724","title":"Large Scale Structure of Neural Network Loss Landscapes","created":"2019-06-11","cited_by_count":68},{"id":"1805.10369","title":"Stable Recurrent Models","created":"2018-05-25","cited_by_count":66},{"id":"2009.11243","title":"Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves","created":"2020-09-23","cited_by_count":58},{"id":"2110.01765","title":"Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping","created":"2021-10-05","cited_by_count":52},{"id":"2112.13835","title":"Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies","created":"2021-12-27","cited_by_count":52},{"id":"1703.03633","title":"Learning Gradient Descent: Better Generalization and Longer Horizons","created":"2017-03-10","cited_by_count":50},{"id":"1912.08866","title":"Continuous Meta-Learning without Tasks","created":"2019-12-18","cited_by_count":50},{"id":"1807.08912","title":"Meta-Learning Priors for Efficient Online Bayesian Regression","created":"2018-07-24","cited_by_count":48},{"id":"1703.00441","title":"Learning to Optimize Neural Nets","created":"2017-03-01","cited_by_count":41},{"id":"1804.00325","title":"Aggregated Momentum: Stability Through Passive Damping","created":"2018-04-01","cited_by_count":36},{"id":"2203.11860","title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","created":"2022-03-22","cited_by_count":32},{"id":"2010.09089","title":"Training Stronger Baselines for Learning to Optimize","created":"2020-10-18","cited_by_count":31},{"id":"2107.10847","title":"Accelerating Quadratic Optimization with Reinforcement Learning","created":"2021-07-22","cited_by_count":30},{"id":"1909.09712","title":"Learning an Adaptive Learning Rate Schedule","created":"2019-09-20","cited_by_count":29},{"id":"2002.11887","title":"Using a thousand optimization tasks to learn hyperparameter search strategies","created":"2020-02-27","cited_by_count":29},{"id":"2106.00958","title":"A Generalizable Approach to Learning Optimizers","created":"2021-06-02","cited_by_count":23},{"id":"2010.00406","title":"Momentum via Primal Averaging: Theoretical Insights and Learning Rate Schedules for Non-Convex Optimization","created":"2020-10-01","cited_by_count":21},{"id":"2011.02159","title":"Reverse engineering learned optimizers reveals known and novel mechanisms","created":"2020-11-04","cited_by_count":19},{"id":"1705.11159","title":"Reinforcement Learning for Learning Rate Control","created":"2017-05-31","cited_by_count":16},{"id":"2203.06578","title":"Symbolic Learning to Optimize: Towards Interpretability and Scalability","created":"2022-03-13","cited_by_count":16},{"id":"1906.03367","title":"Using learned optimizers to make models robust to input noise","created":"2019-06-08","cited_by_count":10},{"id":"2203.00089","title":"Amortized Proximal Optimization","created":"2022-02-28","cited_by_count":9},{"id":"1910.08461","title":"First-Order Preconditioning via Hypergradient Descent","created":"2019-10-18","cited_by_count":8},{"id":"2107.13682","title":"Bayesian Embeddings for Few-Shot Open World Recognition","created":"2021-07-29","cited_by_count":8}],"next_cursor":null}