{"total":2186,"rows":[{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299,"area":null},{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287,"area":null},{"id":"2406.07496","title":"TextGrad: Automatic \"Differentiation\" via Text","created":"2024-06-11","cited_by_count":273,"area":null},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2205.11172","title":"How Powerful are Spectral Graph Neural Networks","created":"2022-05-23","cited_by_count":169,"area":null},{"id":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153,"area":null},{"id":"2209.08037","title":"DAGMA: Learning DAGs via M-matrices and a Log-Determinant Acyclicity Characterization","created":"2022-09-16","cited_by_count":140,"area":null},{"id":"2212.04612","title":"Training Data Influence Analysis and Estimation: A Survey","created":"2022-12-09","cited_by_count":135,"area":null},{"id":"2303.00566","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","created":"2023-03-01","cited_by_count":122,"area":null},{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119,"area":null},{"id":"2311.01453","title":"PPI++: Efficient Prediction-Powered Inference","created":"2023-11-02","cited_by_count":117,"area":null},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"area":null},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2310.00429","title":"On the Stability of Iterative Retraining of Generative Models on their own Data","created":"2023-09-30","cited_by_count":100,"area":null},{"id":"2111.13839","title":"Towards Principled Disentanglement for Domain Generalization","created":"2021-11-27","cited_by_count":91,"area":null},{"id":"2202.00817","title":"Do Differentiable Simulators Give Better Policy Gradients?","created":"2022-02-02","cited_by_count":89,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2206.04920","title":"Fisher SAM: Information Geometry and Sharpness Aware Minimisation","created":"2022-06-10","cited_by_count":84,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2208.11195","title":"Robustness to Unbounded Smoothness of Generalized SignSGD","created":"2022-08-23","cited_by_count":81,"area":null},{"id":"2401.14461","title":"Marabou 2.0: A Versatile Formal Analyzer of Neural Networks","created":"2024-01-25","cited_by_count":81,"area":null},{"id":"2110.13715","title":"ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs","created":"2021-10-26","cited_by_count":78,"area":null},{"id":"2109.05389","title":"Omnipredictors","created":"2021-09-11","cited_by_count":74,"area":null},{"id":"2501.12352","title":"Test-time regression: a unifying framework for designing sequence models with associative memory","created":"2025-01-21","cited_by_count":74,"area":null},{"id":"2301.06197","title":"Who Should Predict? Exact Algorithms For Learning to Defer to Humans","created":"2023-01-15","cited_by_count":70,"area":null},{"id":"2112.11256","title":"Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling","created":"2021-12-21","cited_by_count":66,"area":null},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66,"area":null},{"id":"2302.01772","title":"Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity","created":"2023-02-03","cited_by_count":65,"area":null},{"id":"2203.07034","title":"Active Learning by Feature Mixing","created":"2022-03-14","cited_by_count":63,"area":null},{"id":"2205.12173","title":"Byzantine Machine Learning Made Easy by Resilient Averaging of Momentums","created":"2022-05-24","cited_by_count":63,"area":null},{"id":"2210.08649","title":"Loss Minimization through the Lens of Outcome Indistinguishability","created":"2022-10-16","cited_by_count":62,"area":null},{"id":"2110.14177","title":"Federated Linear Contextual Bandits","created":"2021-10-27","cited_by_count":61,"area":null},{"id":"2110.03237","title":"Score-based Generative Neural Networks for Large-Scale Optimal Transport","created":"2021-10-07","cited_by_count":60,"area":null},{"id":"2207.13887","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","created":"2022-07-28","cited_by_count":60,"area":null},{"id":"2209.11379","title":"Do Current Multi-Task Optimization Methods in Deep Learning Even Help?","created":"2022-09-23","cited_by_count":60,"area":null},{"id":"2202.08312","title":"Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams","created":"2022-02-16","cited_by_count":59,"area":null},{"id":"2209.07089","title":"Constrained Update Projection Approach to Safe Policy Optimization","created":"2022-09-15","cited_by_count":58,"area":null},{"id":"2112.11313","title":"On the Adversarial Robustness of Causal Algorithmic Recourse","created":"2021-12-21","cited_by_count":56,"area":null},{"id":"2402.19078","title":"Smooth Tchebycheff Scalarization for Multi-Objective Optimization","created":"2024-02-29","cited_by_count":54,"area":null},{"id":"2210.08495","title":"Pareto Set Learning for Expensive Multi-Objective Optimization","created":"2022-10-16","cited_by_count":51,"area":null},{"id":"2110.03677","title":"Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect","created":"2021-10-07","cited_by_count":50,"area":null},{"id":"2205.02640","title":"Model-Based Deep Learning: On the Intersection of Deep Learning and Optimization","created":"2022-05-05","cited_by_count":50,"area":null},{"id":"2302.04040","title":"Sample-efficient Multi-objective Molecular Optimization with GFlowNets","created":"2023-02-08","cited_by_count":50,"area":null},{"id":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50,"area":null},{"id":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2306.13461","title":"Understanding quantum machine learning also requires rethinking generalization","created":"2023-06-23","cited_by_count":49,"area":null},{"id":"2201.12191","title":"Kernelized Concept Erasure","created":"2022-01-28","cited_by_count":48,"area":null},{"id":"2411.01679","title":"Autoformulation of Mathematical Optimization Models Using LLMs","created":"2024-11-03","cited_by_count":48,"area":null},{"id":"2106.11344","title":"f-Domain-Adversarial Learning: Theory and Algorithms","created":"2021-06-21","cited_by_count":47,"area":null},{"id":"2307.14023","title":"Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?","created":"2023-07-26","cited_by_count":47,"area":null},{"id":"2202.00089","title":"Understanding AdamW through Proximal Methods and Scale-Freeness","created":"2022-01-31","cited_by_count":46,"area":null},{"id":"2406.09405","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","created":"2024-06-13","cited_by_count":46,"area":null},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45,"area":null},{"id":"2403.01131","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","created":"2024-03-02","cited_by_count":45,"area":null},{"id":"2211.14666","title":"Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning","created":"2022-11-26","cited_by_count":44,"area":null},{"id":"2306.01264","title":"Convex and Non-convex Optimization Under Generalized Smoothness","created":"2023-06-02","cited_by_count":44,"area":null},{"id":"2107.00940","title":"Inverse-Dirichlet Weighting Enables Reliable Training of Physics Informed Neural Networks","created":"2021-07-02","cited_by_count":43,"area":null},{"id":"2201.01985","title":"Jointly Efficient and Optimal Algorithms for Logistic Bandits","created":"2022-01-06","cited_by_count":41,"area":null},{"id":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41,"area":null},{"id":"2502.04664","title":"Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data","created":"2025-02-07","cited_by_count":41,"area":null},{"id":"2203.05816","title":"No Free Lunch Theorem for Security and Utility in Federated Learning","created":"2022-03-11","cited_by_count":39,"area":null},{"id":"2310.05351","title":"Generalized Neural Collapse for a Large Number of Classes","created":"2023-10-09","cited_by_count":39,"area":null},{"id":"2310.06116","title":"OptiMUS: Optimization Modeling Using MIP Solvers and large language models","created":"2023-10-09","cited_by_count":39,"area":null},{"id":"2109.11926","title":"Sinkhorn Distributionally Robust Optimization","created":"2021-09-24","cited_by_count":38,"area":null},{"id":"2202.06491","title":"Adversarial Graph Contrastive Learning with Information Regularization","created":"2022-02-14","cited_by_count":38,"area":null},{"id":"2206.07766","title":"Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2407.19115","title":"Towards Scalable and Stable Parallelization of Nonlinear RNNs","created":"2024-07-26","cited_by_count":38,"area":null},{"id":"2407.19633","title":"OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale","created":"2024-07-29","cited_by_count":38,"area":null},{"id":"2106.05586","title":"Data augmentation in Bayesian neural networks and the cold posterior effect","created":"2021-06-10","cited_by_count":36,"area":null},{"id":"2106.09291","title":"Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion","created":"2021-06-17","cited_by_count":36,"area":null},{"id":"2307.16212","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","created":"2023-07-30","cited_by_count":36,"area":null},{"id":"2601.19156","title":"Convergence of Muon with Newton-Schulz","created":"2026-01-27","cited_by_count":36,"area":null},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35,"area":null},{"id":"2205.01059","title":"Enhanced Physics-Informed Neural Networks with Augmented Lagrangian Relaxation Method (AL-PINNs)","created":"2022-04-29","cited_by_count":35,"area":null},{"id":"2305.16284","title":"DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method","created":"2023-05-25","cited_by_count":35,"area":null},{"id":"2402.09056","title":"Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?","created":"2024-02-14","cited_by_count":35,"area":null},{"id":"2402.17564","title":"Unleashing the Potential of Large Language Models as Prompt Optimizers: Analogical Analysis with Gradient-based Model Optimizers","created":"2024-02-27","cited_by_count":35,"area":null},{"id":"2403.04547","title":"CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?","created":"2024-03-07","cited_by_count":35,"area":null},{"id":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34,"area":null},{"id":"2209.06235","title":"Improving Self-Supervised Learning by Characterizing Idealized Representations","created":"2022-09-13","cited_by_count":34,"area":null},{"id":"2306.03534","title":"Continual Learning in Linear Classification on Separable Data","created":"2023-06-06","cited_by_count":34,"area":null},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2311.07568","title":"Feature emergence via margin maximization: case studies in algebraic tasks","created":"2023-11-13","cited_by_count":33,"area":null},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2302.03201","title":"Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR","created":"2023-02-07","cited_by_count":32,"area":null},{"id":"2207.07256","title":"Improving Task-free Continual Learning by Distributionally Robust Memory Evolution","created":"2022-07-15","cited_by_count":31,"area":null},{"id":"2311.18531","title":"Dataset Distillation via the Wasserstein Metric","created":"2023-11-30","cited_by_count":31,"area":null},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2205.06664","title":"NN-EUCLID: deep-learning hyperelasticity without stress data","created":"2022-05-04","cited_by_count":30,"area":null},{"id":"2307.08336","title":"RAYEN: Imposition of Hard Convex Constraints on Neural Networks","created":"2023-07-17","cited_by_count":30,"area":null},{"id":"2211.05641","title":"Regression as Classification: Influence of Task Formulation on Neural Network Features","created":"2022-11-10","cited_by_count":29,"area":null},{"id":"2302.01404","title":"Provably Bounding Neural Network Preimages","created":"2023-02-02","cited_by_count":29,"area":null},{"id":"2302.02334","title":"Revisiting Discriminative vs. Generative Classifiers: Theory and Implications","created":"2023-02-05","cited_by_count":29,"area":null},{"id":"2407.13977","title":"A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits","created":"2024-07-19","cited_by_count":29,"area":null},{"id":"2411.06019","title":"GaussianSpa: An \"Optimizing-Sparsifying\" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting","created":"2024-11-09","cited_by_count":29,"area":null},{"id":"2201.01702","title":"Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations","created":"2022-01-04","cited_by_count":28,"area":null},{"id":"2205.10129","title":"Topology-aware Graph Neural Networks for Learning Feasible and Adaptive ac-OPF Solutions","created":"2022-05-16","cited_by_count":28,"area":null},{"id":"2208.14673","title":"Incremental Learning in Diagonal Linear Networks","created":"2022-08-31","cited_by_count":28,"area":null}],"next_cursor":"100"}