{"list":"other","total":65,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1703.06114","title":"Deep Sets","created":"2017-03-10","cited_by_count":1421},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"id":"1805.08974","title":"Do Better ImageNet Models Transfer Better?","created":"2018-05-23","cited_by_count":565},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"id":"1908.00709","title":"AutoML: A Survey of the State-of-the-Art","created":"2019-08-02","cited_by_count":390},{"id":"1711.09846","title":"Population Based Training of Neural Networks","created":"2017-11-27","cited_by_count":367},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1703.01785","title":"Forward and Reverse Gradient-Based Hyperparameter Optimization","created":"2017-03-06","cited_by_count":234},{"id":"1502.07943","title":"Non-stochastic Best Arm Identification and Hyperparameter Optimization","created":"2015-02-27","cited_by_count":221},{"id":"1810.01075","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","created":"2018-10-02","cited_by_count":215},{"id":"1611.01232","title":"Deep Information Propagation","created":"2016-11-04","cited_by_count":195},{"id":"2002.12462","title":"LEEP: A New Measure to Evaluate Transferability of Learned Representations","created":"2020-02-27","cited_by_count":188},{"id":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"2102.11005","title":"LogME: Practical Assessment of Pre-trained Models for Transfer Learning","created":"2021-02-22","cited_by_count":172},{"id":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145},{"id":"1908.08142","title":"Transferability and Hardness of Supervised Classification Tasks","created":"2019-08-21","cited_by_count":127},{"id":"1703.06240","title":"Multi-fidelity Bayesian Optimisation with Continuous Approximations","created":"2017-03-18","cited_by_count":121},{"id":"2003.05689","title":"Hyper-Parameter Optimization: A Review of Algorithms and Applications","created":"2020-03-12","cited_by_count":114},{"id":"1810.00113","title":"Predicting the Generalization Gap in Deep Networks with Margin Distributions","created":"2018-09-28","cited_by_count":113},{"id":"2002.11448","title":"Predicting Neural Network Accuracy from Weights","created":"2020-02-26","cited_by_count":110},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107},{"id":"1903.03088","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","created":"2019-03-07","cited_by_count":105},{"id":"2104.01177","title":"How Powerful are Performance Predictors in Neural Architecture Search?","created":"2021-04-02","cited_by_count":90},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86},{"id":"2002.05551","title":"PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees","created":"2020-02-13","cited_by_count":85},{"id":"1603.00389","title":"Multi-Information Source Optimization","created":"2016-03-01","cited_by_count":84},{"id":"1802.09419","title":"Stochastic Hyperparameter Optimization through Hypernetworks","created":"2018-02-26","cited_by_count":73},{"id":"2101.07667","title":"Few-Shot Bayesian Optimization with Deep Kernel Surrogates","created":"2021-01-19","cited_by_count":71},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71},{"id":"1904.02642","title":"Meta-Learning Acquisition Functions for Transfer Learning in Bayesian Optimization","created":"2019-04-04","cited_by_count":70},{"id":"2002.05688","title":"Classifying the classifier: dissecting the weight space of neural networks","created":"2020-02-13","cited_by_count":65},{"id":"2206.14262","title":"Supervised Training of Conditional Monge Maps","created":"2022-06-28","cited_by_count":61},{"id":"2007.03117","title":"Multi-Fidelity Bayesian Optimization via Deep Neural Networks","created":"2020-07-06","cited_by_count":46},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39},{"id":"2403.15385","title":"LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis","created":"2024-03-22","cited_by_count":39},{"id":"2212.14032","title":"On Implicit Bias in Overparameterized Bilevel Optimization","created":"2022-12-28","cited_by_count":30},{"id":"2110.10545","title":"Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs","created":"2021-10-20","cited_by_count":28},{"id":"2111.01754","title":"Meta-Learning to Improve Pre-Training","created":"2021-11-02","cited_by_count":27},{"id":"2311.14645","title":"A General Framework for User-Guided Bayesian Optimization","created":"2023-11-24","cited_by_count":22},{"id":"1608.03585","title":"Warm Starting Bayesian Optimization","created":"2016-08-11","cited_by_count":21},{"id":"1906.01550","title":"Towards Task and Architecture-Independent Generalization Gap Predictors","created":"2019-06-04","cited_by_count":18},{"id":"2212.03905","title":"Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve","created":"2022-12-07","cited_by_count":18},{"id":"2010.13514","title":"Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians","created":"2020-10-26","cited_by_count":17},{"id":"2202.09774","title":"Supervising the Multi-Fidelity Race of Hyperparameter Configurations","created":"2022-02-20","cited_by_count":15},{"id":"1904.00438","title":"Understanding Neural Architecture Search Techniques","created":"2019-03-31","cited_by_count":12},{"id":"2106.15356","title":"Scalable Gaussian Processes for Data-Driven Design using Big Data with Categorical Factors","created":"2021-06-26","cited_by_count":11},{"id":"1911.09336","title":"Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS","created":"2019-11-21","cited_by_count":8},{"id":"2208.12754","title":"Task Selection for AutoML System Evaluation","created":"2022-08-26","cited_by_count":7},{"id":"2404.19157","title":"Scalable Bayesian Inference in the Era of Deep Learning: From Gaussian Processes to Deep Neural Networks","created":"2024-04-29","cited_by_count":1}],"next_cursor":null}