{"total":111,"rows":[{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2306.10374","title":"A Survey of Contextual Optimization Methods for Decision Making under Uncertainty","created":"2023-06-17","cited_by_count":82,"area":null},{"id":"2305.18764","title":"When Does Optimizing a Proper Loss Yield Calibration?","created":"2023-05-30","cited_by_count":36,"area":null},{"id":"2312.17346","title":"STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction","created":"2023-12-28","cited_by_count":35,"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":"2206.14234","title":"PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming","created":"2022-06-28","cited_by_count":32,"area":null},{"id":"2209.15466","title":"Sparsity-Constrained Optimal Transport","created":"2022-09-30","cited_by_count":32,"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":"2206.02353","title":"Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2207.08768","title":"Rank-based Decomposable Losses in Machine Learning: A Survey","created":"2022-07-18","cited_by_count":26,"area":null},{"id":"2302.01425","title":"Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective","created":"2023-02-02","cited_by_count":26,"area":null},{"id":"2506.16640","title":"Long-Context Generalization with Sparse Attention","created":"2025-06-19","cited_by_count":21,"area":null},{"id":"2304.09424","title":"Loss Minimization Yields Multicalibration for Large Neural Networks","created":"2023-04-19","cited_by_count":19,"area":null},{"id":"2103.09879","title":"Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking","created":"2021-03-17","cited_by_count":14,"area":null},{"id":"2108.01988","title":"Sparse Continuous Distributions and Fenchel-Young Losses","created":"2021-08-04","cited_by_count":14,"area":null},{"id":"2305.16358","title":"Differentiable Clustering with Perturbed Spanning Forests","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2310.15903","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2405.17454","title":"Generative AI for the Optimization of Next-Generation Wireless Networks: Basics, State-of-the-Art, and Open Challenges","created":"2024-05-22","cited_by_count":14,"area":null},{"id":"2301.11260","title":"Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear Programming","created":"2023-01-26","cited_by_count":13,"area":null},{"id":"2402.13725","title":"Sparse and Structured Hopfield Networks","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2102.00760","title":"Fast rates in structured prediction","created":"2021-02-01","cited_by_count":11,"area":null},{"id":"2103.10291","title":"Smoothing and Shrinking the Sparse Seq2Seq Search Space","created":"2021-03-18","cited_by_count":11,"area":null},{"id":"2304.00789","title":"Combinatorial Optimization enriched Machine Learning to solve the Dynamic Vehicle Routing Problem with Time Windows","created":"2023-04-03","cited_by_count":10,"area":null},{"id":"2501.18537","title":"Loss Functions and Operators Generated by f-Divergences","created":"2025-01-30","cited_by_count":10,"area":null},{"id":"2503.00626","title":"Dissecting the Impact of Model Misspecification in Data-driven Optimization","created":"2025-03-01","cited_by_count":10,"area":null},{"id":"2505.19371","title":"Foundations of Top-$k$ Decoding For Language Models","created":"2025-05-25","cited_by_count":10,"area":null},{"id":"2505.22224","title":"Solver-Free Decision-Focused Learning for Linear Optimization Problems","created":"2025-05-28","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":"2405.14064","title":"Building a stable classifier with the inflated argmax","created":"2024-05-22","cited_by_count":8,"area":null},{"id":"2405.18979","title":"MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2405.19532","title":"Contrasting Multiple Representations with the Multi-Marginal Matching Gap","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2501.13648","title":"Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel$-$Young Loss Perspective and Gap-Dependent Regret Analysis","created":"2025-01-23","cited_by_count":8,"area":null},{"id":"2207.04387","title":"Bregman Proximal Langevin Monte Carlo via Bregman--Moreau Envelopes","created":"2022-07-10","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":"2104.03046","title":"Multimodal Continuous Visual Attention Mechanisms","created":"2021-04-07","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":"2407.05920","title":"LPGD: A General Framework for Backpropagation through Embedded Optimization Layers","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2501.18581","title":"Bias-variance decompositions: the exclusive privilege of Bregman divergences","created":"2025-01-30","cited_by_count":6,"area":null},{"id":"2102.13416","title":"Moreau-Yosida $f$-divergences","created":"2021-02-26","cited_by_count":5,"area":null},{"id":"2105.15069","title":"On the Consistency of Max-Margin Losses","created":"2021-05-31","cited_by_count":5,"area":null},{"id":"2101.01082","title":"Learning to solve the single machine scheduling problem with release times and sum of completion times","created":"2021-01-04","cited_by_count":4,"area":null},{"id":"2409.07131","title":"Reranking Laws for Language Generation: A Communication-Theoretic Perspective","created":"2024-09-11","cited_by_count":4,"area":null},{"id":"2409.16243","title":"A fast and sound tagging method for discontinuous named-entity recognition","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2505.04757","title":"Primal-dual algorithm for contextual stochastic combinatorial optimization","created":"2025-05-07","cited_by_count":4,"area":null},{"id":"2209.07481","title":"Variational Representations of Annealing Paths: Bregman Information under Monotonic Embedding","created":"2022-09-15","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":"2407.10417","title":"Proper losses regret at least 1/2-order","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2407.17200","title":"Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems","created":"2024-07-24","cited_by_count":3,"area":null},{"id":"2410.06656","title":"WardropNet: Traffic Flow Predictions via Equilibrium-Augmented Learning","created":"2024-10-09","cited_by_count":3,"area":null},{"id":"2411.00119","title":"Soft Condorcet Optimization for Ranking of General Agents","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2501.18528","title":"Joint Learning of Energy-based Models and their Partition Function","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2510.18215","title":"The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2511.00907","title":"Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2511.15146","title":"Beyond Uncertainty Sets: Leveraging Optimal Transport to Extend Conformal Predictive Distributions to Multivariate Settings","created":"2025-11-19","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":"2301.10810","title":"On the inconsistency of separable losses for structured prediction","created":"2023-01-25","cited_by_count":2,"area":null},{"id":"2302.07679","title":"On graph-based reentrancy-free semantic parsing","created":"2023-02-15","cited_by_count":2,"area":null},{"id":"2311.15112","title":"Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts","created":"2023-11-25","cited_by_count":2,"area":null},{"id":"2312.00640","title":"One to beat them all: \"RYU\" -- a unifying framework for the construction of safe balls","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2408.04175","title":"pyBregMan: A Python library for Bregman Manifolds","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2410.19055","title":"Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2502.14773","title":"Sparse Activations as Conformal Predictors","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2505.09432","title":"Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel-Young Losses","created":"2025-05-14","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":"2508.11365","title":"Minimizing Surrogate Losses for Decision-Focused Learning using Differentiable Optimization","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2509.15641","title":"Information Geometry of Variational Bayes","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2103.02893","title":"Lower-Bounded Proper Losses for Weakly Supervised Classification","created":"2021-03-04","cited_by_count":1,"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":"2301.11476","title":"Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence","created":"2023-01-27","cited_by_count":1,"area":null},{"id":"2302.12059","title":"A Statistical Learning Take on the Concordance Index for Survival Analysis","created":"2023-02-23","cited_by_count":1,"area":null},{"id":"2304.03202","title":"SLM: End-to-end Feature Selection via Sparse Learnable Masks","created":"2023-04-06","cited_by_count":1,"area":null},{"id":"2402.10818","title":"Trading off Consistency and Dimensionality of Convex Surrogates for the Mode","created":"2024-02-16","cited_by_count":1,"area":null},{"id":"2406.05666","title":"Probability Distribution Learning and Its Application in Deep Learning","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2412.08287","title":"DistrictNet: Decision-aware learning for geographical districting","created":"2024-12-11","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":"2601.21775","title":"Differentiable Knapsack and Top-k Operators via Dynamic Programming","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.04812","title":"Quadratic polarity and polar Fenchel-Young divergences from the canonical Legendre polarity","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.10452","title":"Brenier Isotonic Regression","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2606.03332","title":"Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference","created":"2026-06-02","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":"2609.17629","title":"Fenchel-Young Duality Gaps: Certified Early Stopping for Regularized Inverse Problems","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2112.08200","title":"Taming Overconfident Prediction on Unlabeled Data from Hindsight","created":"2021-12-15","cited_by_count":0,"area":null},{"id":"2308.08886","title":"Dual Gauss-Newton Directions for Deep Learning","created":"2023-08-17","cited_by_count":0,"area":null},{"id":"2311.16487","title":"On the Robustness of Decision-Focused Learning","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2407.02279","title":"How to Boost Any Loss Function","created":"2024-07-02","cited_by_count":0,"area":null},{"id":"2411.03535","title":"The Differentiable Feasibility Pump","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2412.00426","title":"Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection","created":"2024-11-30","cited_by_count":0,"area":null},{"id":"2502.16120","title":"A Fenchel-Young Loss Approach to Data-Driven Inverse Optimization","created":"2025-02-22","cited_by_count":0,"area":null},{"id":"2503.07818","title":"Strengthening the Internal Adversarial Robustness in Lifted Neural Networks","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2503.23016","title":"Towards Understanding the Optimization Mechanisms in Deep Learning","created":"2025-03-29","cited_by_count":0,"area":null},{"id":"2506.19125","title":"Transformer Circuits Can Realize Clustering Algorithms","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2508.20978","title":"Scaling Neuro-symbolic Problem Solving: Solver-Free Learning of Constraints and Objectives","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.15999","title":"Inverse Optimization Latent Variable Models for Learning Costs Applied to Route Problems","created":"2025-09-19","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":"2601.13410","title":"Classifiers in High Dimensional Hilbert Metrics","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2601.21883","title":"Managing Solution Stability in Decision-Focused Learning with Cost Regularization","created":"2026-01-29","cited_by_count":0,"area":null}],"next_cursor":"100"}