{"list":"other","total":60,"rows":[{"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":"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":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1810.02340","title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","created":"2018-10-04","cited_by_count":812},{"id":"1811.03962","title":"A Convergence Theory for Deep Learning via Over-Parameterization","created":"2018-11-09","cited_by_count":787},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"id":"1603.06560","title":"Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization","created":"2016-03-21","cited_by_count":699},{"id":"1703.04247","title":"DeepFM: A Factorization-Machine based Neural Network for CTR Prediction","created":"2017-03-13","cited_by_count":676},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674},{"id":"1706.02515","title":"Self-Normalizing Neural Networks","created":"2017-06-08","cited_by_count":598},{"id":"2309.07597","title":"C-Pack: Packed Resources For General Chinese Embeddings","created":"2023-09-14","cited_by_count":578},{"id":"1904.11955","title":"On Exact Computation with an Infinitely Wide Neural Net","created":"2019-04-26","cited_by_count":573},{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"2006.05467","title":"Pruning neural networks without any data by iteratively conserving synaptic flow","created":"2020-06-09","cited_by_count":479},{"id":"2002.07376","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","created":"2020-02-18","cited_by_count":471},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"2001.00326","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","created":"2020-01-02","cited_by_count":416},{"id":"1902.09635","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","created":"2019-02-25","cited_by_count":344},{"id":"1810.11921","title":"AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks","created":"2018-10-29","cited_by_count":320},{"id":"1606.05336","title":"On the Expressive Power of Deep Neural Networks","created":"2016-06-16","cited_by_count":306},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"2402.01613","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","created":"2024-02-02","cited_by_count":265},{"id":"2006.02903","title":"A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions","created":"2020-06-01","cited_by_count":254},{"id":"2006.04647","title":"Neural Architecture Search without Training","created":"2020-06-08","cited_by_count":244},{"id":"2305.02997","title":"When Do Neural Nets Outperform Boosted Trees on Tabular Data?","created":"2023-05-04","cited_by_count":223},{"id":"1502.07943","title":"Non-stochastic Best Arm Identification and Hyperparameter Optimization","created":"2015-02-27","cited_by_count":221},{"id":"2101.08134","title":"Zero-Cost Proxies for Lightweight NAS","created":"2021-01-20","cited_by_count":199},{"id":"2102.11535","title":"Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective","created":"2021-02-23","cited_by_count":169},{"id":"1901.09021","title":"Complexity of Linear Regions in Deep Networks","created":"2019-01-25","cited_by_count":167},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139},{"id":"1303.4402","title":"From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews","created":"2013-03-18","cited_by_count":108},{"id":"1801.05787","title":"Faster gaze prediction with dense networks and Fisher pruning","created":"2018-01-17","cited_by_count":94},{"id":"2301.11300","title":"ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients","created":"2023-01-26","cited_by_count":58},{"id":"2403.01841","title":"Making Pre-trained Language Models Great on Tabular Prediction","created":"2024-03-04","cited_by_count":57},{"id":"2206.15306","title":"Transfer Learning with Deep Tabular Models","created":"2022-06-30","cited_by_count":52},{"id":"1705.05355","title":"Probabilistic Matrix Factorization for Automated Machine Learning","created":"2017-05-15","cited_by_count":31},{"id":"1808.03233","title":"OBOE: Collaborative Filtering for AutoML Model Selection","created":"2018-08-09","cited_by_count":31},{"id":"2109.00817","title":"NASI: Label- and Data-agnostic Neural Architecture Search at Initialization","created":"2021-09-02","cited_by_count":28},{"id":"1906.04113","title":"BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget","created":"2019-06-10","cited_by_count":26},{"id":"2107.01830","title":"ARM-Net: Adaptive Relation Modeling Network for Structured Data","created":"2021-07-05","cited_by_count":24},{"id":"2402.14335","title":"HyperFast: Instant Classification for Tabular Data","created":"2024-02-22","cited_by_count":22},{"id":"2201.09785","title":"Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search","created":"2022-01-24","cited_by_count":17},{"id":"1912.10729","title":"TextNAS: A Neural Architecture Search Space tailored for Text Representation","created":"2019-12-23","cited_by_count":16},{"id":"2207.12534","title":"Trainability Preserving Neural Pruning","created":"2022-07-25","cited_by_count":16},{"id":"2212.00522","title":"CL4CTR: A Contrastive Learning Framework for CTR Prediction","created":"2022-12-01","cited_by_count":14},{"id":"2007.14573","title":"FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data","created":"2020-07-29","cited_by_count":13},{"id":"2207.06940","title":"PASHA: Efficient HPO and NAS with Progressive Resource Allocation","created":"2022-07-14","cited_by_count":13},{"id":"2010.16358","title":"AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-Parallel Training for Tabular Data","created":"2020-10-30","cited_by_count":9},{"id":"2312.16831","title":"METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection","created":"2023-12-28","cited_by_count":9},{"id":"2403.02484","title":"Encodings for Prediction-based Neural Architecture Search","created":"2024-03-04","cited_by_count":9},{"id":"2210.12001","title":"When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work","created":"2022-10-21","cited_by_count":8},{"id":"2402.02334","title":"Arithmetic Feature Interaction Is Necessary for Deep Tabular Learning","created":"2024-02-04","cited_by_count":8},{"id":"2204.07615","title":"TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets","created":"2022-04-15","cited_by_count":6},{"id":"2305.16948","title":"Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets","created":"2023-05-26","cited_by_count":1}],"next_cursor":null}