{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1610.01145","title":"Error bounds for approximations with deep ReLU networks","created":"2016-10-03","cited_by_count":574},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"1711.09485","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","created":"2017-11-26","cited_by_count":332},{"id":"1412.8690","title":"Breaking the Curse of Dimensionality with Convex Neural Networks","created":"2014-12-30","cited_by_count":331},{"id":"1709.02540","title":"The Expressive Power of Neural Networks: A View from the Width","created":"2017-09-08","cited_by_count":320},{"id":"1703.02930","title":"Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks","created":"2017-03-08","cited_by_count":311},{"id":"1802.03620","title":"Optimal approximation of continuous functions by very deep ReLU networks","created":"2018-02-10","cited_by_count":166},{"id":"2001.03040","title":"Deep Network Approximation for Smooth Functions","created":"2020-01-09","cited_by_count":164},{"id":"1810.08033","title":"Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality","created":"2018-10-18","cited_by_count":162},{"id":"1804.10306","title":"Universal approximations of invariant maps by neural networks","created":"2018-04-26","cited_by_count":127},{"id":"2103.00502","title":"Optimal Approximation Rate of ReLU Networks in terms of Width and Depth","created":"2021-02-28","cited_by_count":96},{"id":"1902.07896","title":"Error bounds for approximations with deep ReLU neural networks in $W^{s,p}$ norms","created":"2019-02-21","cited_by_count":95},{"id":"1705.01714","title":"Optimal Approximation with Sparsely Connected Deep Neural Networks","created":"2017-05-04","cited_by_count":91},{"id":"1906.09477","title":"The phase diagram of approximation rates for deep neural networks","created":"2019-06-22","cited_by_count":88},{"id":"2006.04862","title":"$O(n)$ Connections are Expressive Enough: Universal Approximability of Sparse Transformers","created":"2020-06-08","cited_by_count":83},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82},{"id":"2104.08938","title":"On the approximation of functions by tanh neural networks","created":"2021-04-18","cited_by_count":81},{"id":"1507.00473","title":"The Optimal Sample Complexity of PAC Learning","created":"2015-07-02","cited_by_count":72},{"id":"2203.01550","title":"A Characterization of Multiclass Learnability","created":"2022-03-03","cited_by_count":67},{"id":"2002.05933","title":"Approximation Bounds for Random Neural Networks and Reservoir Systems","created":"2020-02-14","cited_by_count":52},{"id":"2101.05390","title":"Universal Approximation Theorems for Differentiable Geometric Deep Learning","created":"2021-01-13","cited_by_count":41},{"id":"2106.14472","title":"Hyperbolic Busemann Learning with Ideal Prototypes","created":"2021-06-28","cited_by_count":41},{"id":"2107.02397","title":"Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons","created":"2021-07-06","cited_by_count":41},{"id":"1712.00754","title":"Universal discrete-time reservoir computers with stochastic inputs and linear readouts using non-homogeneous state-affine systems","created":"2017-12-03","cited_by_count":39},{"id":"1909.11722","title":"A Theoretical Analysis of the Number of Shots in Few-Shot Learning","created":"2019-09-25","cited_by_count":39},{"id":"1809.00973","title":"Equivalence of approximation by convolutional neural networks and fully-connected networks","created":"2018-09-04","cited_by_count":38},{"id":"2102.10911","title":"Elementary superexpressive activations","created":"2021-02-22","cited_by_count":36},{"id":"2010.12047","title":"Fading memory echo state networks are universal","created":"2020-10-22","cited_by_count":32},{"id":"2012.03351","title":"The universal approximation theorem for complex-valued neural networks","created":"2020-12-06","cited_by_count":28},{"id":"2210.10253","title":"On the Adversarial Robustness of Mixture of Experts","created":"2022-10-19","cited_by_count":28},{"id":"2201.13094","title":"Designing Universal Causal Deep Learning Models: The Geometric (Hyper)Transformer","created":"2022-01-31","cited_by_count":22},{"id":"2210.13300","title":"Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysis","created":"2022-10-24","cited_by_count":22},{"id":"2305.06324","title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception","created":"2023-05-10","cited_by_count":19},{"id":"2306.03303","title":"Global universal approximation of functional input maps on weighted spaces","created":"2023-06-05","cited_by_count":19},{"id":"2007.06007","title":"Universal Approximation Power of Deep Residual Neural Networks via Nonlinear Control Theory","created":"2020-07-12","cited_by_count":18},{"id":"2304.01561","title":"Optimal rates of approximation by shallow ReLU$^k$ neural networks and applications to nonparametric regression","created":"2023-04-04","cited_by_count":15},{"id":"2211.13866","title":"Minimal Width for Universal Property of Deep RNN","created":"2022-11-25","cited_by_count":12},{"id":"2307.12461","title":"Rates of Approximation by ReLU Shallow Neural Networks","created":"2023-07-24","cited_by_count":12},{"id":"2103.00542","title":"Deep Neural Networks with ReLU-Sine-Exponential Activations Break Curse of Dimensionality in Approximation on H\\\"older Class","created":"2021-02-28","cited_by_count":7},{"id":"2007.00118","title":"Approximation Theory of Tree Tensor Networks: Tensorized Univariate Functions -- Part I","created":"2020-06-30","cited_by_count":6},{"id":"2204.11231","title":"Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions?","created":"2022-04-24","cited_by_count":6},{"id":"2010.15571","title":"Learning Sub-Patterns in Piecewise Continuous Functions","created":"2020-10-29","cited_by_count":4},{"id":"2105.02556","title":"Metric Entropy Limits on Recurrent Neural Network Learning of Linear Dynamical Systems","created":"2021-05-06","cited_by_count":4},{"id":"2202.12166","title":"Attention Enables Zero Approximation Error","created":"2022-02-24","cited_by_count":4},{"id":"2207.06775","title":"Strain-Minimizing Hyperbolic Network Embeddings with Landmarks","created":"2022-07-14","cited_by_count":1}],"next_cursor":null}