{"total":62,"rows":[{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452,"area":"offlinerl"},{"id":"2105.15183","title":"Efficient and Modular Implicit Differentiation","created":"2021-05-31","cited_by_count":203,"area":null},{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138,"area":null},{"id":"2106.01798","title":"Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions","created":"2021-06-03","cited_by_count":98,"area":null},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2105.02343","title":"CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints","created":"2021-05-05","cited_by_count":49,"area":null},{"id":"2210.01941","title":"SIMPLE: A Gradient Estimator for $k$-Subset Sampling","created":"2022-10-04","cited_by_count":34,"area":null},{"id":"2307.13917","title":"BayesDAG: Gradient-Based Posterior Inference for Causal Discovery","created":"2023-07-26","cited_by_count":33,"area":null},{"id":"2106.01087","title":"Is Sparse Attention more Interpretable?","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2207.13513","title":"Learning with Combinatorial Optimization Layers: a Probabilistic Approach","created":"2022-07-27","cited_by_count":29,"area":null},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2305.17075","title":"CREST: A Joint Framework for Rationalization and Counterfactual Text Generation","created":"2023-05-26","cited_by_count":24,"area":null},{"id":"2303.09992","title":"LION: Implicit Vision Prompt Tuning","created":"2023-03-17","cited_by_count":22,"area":null},{"id":"2109.04552","title":"SPECTRA: Sparse Structured Text Rationalization","created":"2021-09-09","cited_by_count":19,"area":null},{"id":"2106.03257","title":"Structured Reordering for Modeling Latent Alignments in Sequence Transduction","created":"2021-06-06","cited_by_count":17,"area":null},{"id":"2106.06038","title":"Modeling Hierarchical Structures with Continuous Recursive Neural Networks","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2402.13725","title":"Sparse and Structured Hopfield Networks","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2209.04862","title":"Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models","created":"2022-09-11","cited_by_count":12,"area":null},{"id":"2102.07456","title":"Neuro-algorithmic Policies enable Fast Combinatorial Generalization","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2104.00428","title":"Storchastic: A Framework for General Stochastic Automatic Differentiation","created":"2021-04-01","cited_by_count":11,"area":null},{"id":"2309.08406","title":"Constraint-Free Structure Learning with Smooth Acyclic Orientations","created":"2023-09-15","cited_by_count":10,"area":null},{"id":"2410.06324","title":"Differentiation Through Black-Box Quadratic Programming Solvers","created":"2024-10-08","cited_by_count":10,"area":null},{"id":"2109.06316","title":"Learning Constraints and Descriptive Segmentation for Subevent Detection","created":"2021-09-13","cited_by_count":9,"area":null},{"id":"2301.11898","title":"DAG Learning on the Permutahedron","created":"2023-01-27","cited_by_count":9,"area":null},{"id":"2205.09589","title":"Learning Energy Networks with Generalized Fenchel-Young Losses","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2104.05819","title":"Learning from Executions for Semantic Parsing","created":"2021-04-12","cited_by_count":7,"area":null},{"id":"2208.03727","title":"Robust Multi-Object Tracking by Marginal Inference","created":"2022-08-07","cited_by_count":7,"area":null},{"id":"2402.08180","title":"Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss","created":"2024-02-13","cited_by_count":7,"area":null},{"id":"2106.07306","title":"Constraining Linear-chain CRFs to Regular Languages","created":"2021-06-14","cited_by_count":6,"area":null},{"id":"2110.14182","title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2205.15814","title":"Contrasting quadratic assignments for set-based representation learning","created":"2022-05-31","cited_by_count":6,"area":null},{"id":"2306.06119","title":"Doubly Stochastic Graph-based Non-autoregressive Reaction Prediction","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2407.05920","title":"LPGD: A General Framework for Backpropagation through Embedded Optimization Layers","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2302.10128","title":"Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels","created":"2023-02-20","cited_by_count":5,"area":null},{"id":"2308.07480","title":"Order-based Structure Learning with Normalizing Flows","created":"2023-08-14","cited_by_count":5,"area":null},{"id":"2306.15103","title":"Structured Dialogue Discourse Parsing","created":"2023-06-26","cited_by_count":4,"area":null},{"id":"2307.10779","title":"Efficient Beam Tree Recursion","created":"2023-07-20","cited_by_count":4,"area":null},{"id":"2104.04391","title":"Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics","created":"2021-04-09","cited_by_count":3,"area":null},{"id":"2405.14574","title":"Learning with Fitzpatrick Losses","created":"2024-05-23","cited_by_count":3,"area":null},{"id":"2108.02658","title":"Sparse Communication via Mixed Distributions","created":"2021-08-05","cited_by_count":2,"area":null},{"id":"2201.00490","title":"Learning with Latent Structures in Natural Language Processing: A Survey","created":"2022-01-03","cited_by_count":2,"area":null},{"id":"2205.01324","title":"Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2209.15176","title":"Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition","created":"2022-09-30","cited_by_count":2,"area":null},{"id":"2307.14193","title":"Efficient Learning of Discrete-Continuous Computation Graphs","created":"2023-07-26","cited_by_count":2,"area":null},{"id":"2505.14240","title":"Learning with Local Search MCMC Layers","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2104.00755","title":"Reconciling the Discrete-Continuous Divide: Towards a Mathematical Theory of Sparse Communication","created":"2021-04-01","cited_by_count":1,"area":null},{"id":"2502.04889","title":"Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses","created":"2025-02-07","cited_by_count":1,"area":null},{"id":"2502.10295","title":"Fenchel-Young Variational Learning","created":"2025-02-14","cited_by_count":1,"area":null},{"id":"2502.18709","title":"Bandit and Delayed Feedback in Online Structured Prediction","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2506.00732","title":"Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2506.10572","title":"Probability Bounding: Post-Hoc Calibration via Box-Constrained Softmax","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2602.03297","title":"Lipschitz Multiscale Deep Equilibrium Models: A Theoretically Guaranteed and Accelerated Approach","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2608.02938","title":"When Should Graph Attention Be Sparse? Learning a Per-Edge Tsallis Index","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2307.08013","title":"Revisiting Implicit Models: Sparsity Trade-offs Capability in Weight-tied Model for Vision Tasks","created":"2023-07-16","cited_by_count":0,"area":null},{"id":"2406.02180","title":"On The Statistical Representation Properties Of The Perturb-Softmax And The Perturb-Argmax Probability Distributions","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2510.07086","title":"Non-Stationary Online Structured Prediction with Surrogate Losses","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2601.22745","title":"Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2606.02294","title":"Regularized Large Neighborhood Search","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.06941","title":"Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2607.01185","title":"Neural Certificate Pricing for Combinatorial Optimization Problems","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.24007","title":"Smooth Learning with Hard Constraints via Legendre-Regularized Policies","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2610.01980","title":"The Curvature of Regret in Contextual Linear Optimization","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}