{"total":192,"rows":[{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178,"area":null},{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138,"area":null},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109,"area":null},{"id":"2201.12091","title":"Linear Adversarial Concept Erasure","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2111.05803","title":"Gradients are Not All You Need","created":"2021-11-10","cited_by_count":86,"area":null},{"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":"2207.09442","title":"Theseus: A Library for Differentiable Nonlinear Optimization","created":"2022-07-19","cited_by_count":65,"area":null},{"id":"2111.14580","title":"Amortized Implicit Differentiation for Stochastic Bilevel Optimization","created":"2021-11-29","cited_by_count":63,"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":"2207.08675","title":"Learning differentiable solvers for systems with hard constraints","created":"2022-07-18","cited_by_count":34,"area":null},{"id":"2304.07939","title":"Leveraging sparse and shared feature activations for disentangled representation learning","created":"2023-04-17","cited_by_count":32,"area":null},{"id":"2212.14032","title":"On Implicit Bias in Overparameterized Bilevel Optimization","created":"2022-12-28","cited_by_count":30,"area":null},{"id":"2209.10780","title":"Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation","created":"2022-09-22","cited_by_count":29,"area":null},{"id":"2205.06688","title":"A Unified Framework for Implicit Sinkhorn Differentiation","created":"2022-05-13","cited_by_count":28,"area":null},{"id":"2305.13768","title":"One-step differentiation of iterative algorithms","created":"2023-05-23","cited_by_count":28,"area":null},{"id":"2207.02849","title":"Betty: An Automatic Differentiation Library for Multilevel Optimization","created":"2022-07-05","cited_by_count":27,"area":null},{"id":"2301.11355","title":"Rigid Body Flows for Sampling Molecular Crystal Structures","created":"2023-01-26","cited_by_count":27,"area":null},{"id":"2305.05080","title":"Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey","created":"2023-05-08","cited_by_count":27,"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":"2206.00457","title":"Automatic differentiation of nonsmooth iterative algorithms","created":"2022-05-31","cited_by_count":25,"area":null},{"id":"2402.05468","title":"Implicit Diffusion: Efficient Optimization through Stochastic Sampling","created":"2024-02-08","cited_by_count":24,"area":null},{"id":"2208.13825","title":"Differentiable Programming for Earth System Modeling","created":"2022-08-29","cited_by_count":22,"area":null},{"id":"2210.01802","title":"Alternating Differentiation for Optimization Layers","created":"2022-10-03","cited_by_count":22,"area":null},{"id":"2210.05577","title":"What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?","created":"2022-10-11","cited_by_count":21,"area":null},{"id":"2310.18605","title":"TorchDEQ: A Library for Deep Equilibrium Models","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2506.00362","title":"FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees","created":"2025-05-31","cited_by_count":21,"area":null},{"id":"2403.20233","title":"Functional Bilevel Optimization for Machine Learning","created":"2024-03-29","cited_by_count":20,"area":null},{"id":"2112.07464","title":"Efficient differentiable quadratic programming layers: an ADMM approach","created":"2021-12-14","cited_by_count":19,"area":null},{"id":"2508.10480","title":"Pinet: Optimizing hard-constrained neural networks with orthogonal projection layers","created":"2025-08-14","cited_by_count":19,"area":null},{"id":"2111.12193","title":"Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation","created":"2021-11-23","cited_by_count":17,"area":null},{"id":"2211.06934","title":"TorchOpt: An Efficient Library for Differentiable Optimization","created":"2022-11-13","cited_by_count":17,"area":null},{"id":"2301.13737","title":"Self-Consistent Velocity Matching of Probability Flows","created":"2023-01-31","cited_by_count":17,"area":null},{"id":"2310.05674","title":"Making Scalable Meta Learning Practical","created":"2023-10-09","cited_by_count":17,"area":null},{"id":"2403.04670","title":"End-to-end Conditional Robust Optimization","created":"2024-03-07","cited_by_count":17,"area":null},{"id":"2206.06135","title":"Flexible Differentiable Optimization via Model Transformations","created":"2022-06-10","cited_by_count":16,"area":null},{"id":"2209.13271","title":"The Curse of Unrolling: Rate of Differentiating Through Optimization","created":"2022-09-27","cited_by_count":16,"area":null},{"id":"2305.16358","title":"Differentiable Clustering with Perturbed Spanning Forests","created":"2023-05-25","cited_by_count":14,"area":null},{"id":"2304.14082","title":"JaxPruner: A concise library for sparsity research","created":"2023-04-27","cited_by_count":13,"area":null},{"id":"2106.01680","title":"Convergent Graph Solvers","created":"2021-06-03","cited_by_count":12,"area":null},{"id":"2301.13395","title":"Differentiating Through Integer Linear Programs with Quadratic Regularization and Davis-Yin Splitting","created":"2023-01-31","cited_by_count":11,"area":null},{"id":"2305.16543","title":"Revisiting Structured Variational Autoencoders","created":"2023-05-25","cited_by_count":11,"area":null},{"id":"2312.05250","title":"TaskMet: Task-Driven Metric Learning for Model Learning","created":"2023-12-08","cited_by_count":11,"area":null},{"id":"2504.01212","title":"Cooper: A Library for Constrained Optimization in Deep Learning","created":"2025-04-01","cited_by_count":11,"area":null},{"id":"2407.13954","title":"Neural topology optimization: the good, the bad, and the ugly","created":"2024-07-19","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":"2411.19285","title":"BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning","created":"2024-11-28","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":"2207.01499","title":"j-Wave: An open-source differentiable wave simulator","created":"2022-06-30","cited_by_count":9,"area":null},{"id":"2207.05636","title":"Neural Posterior Estimation with Differentiable Simulators","created":"2022-07-12","cited_by_count":9,"area":null},{"id":"2506.07003","title":"End-to-End Probabilistic Framework for Learning with Hard Constraints","created":"2025-06-08","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":"2302.09726","title":"Nystrom Method for Accurate and Scalable Implicit Differentiation","created":"2023-02-20","cited_by_count":8,"area":null},{"id":"2308.15020","title":"Massively Parallel Continuous Local Search for Hybrid SAT Solving on GPUs","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2402.13984","title":"Stability-Aware Training of Machine Learning Force Fields with Differentiable Boltzmann Estimators","created":"2024-02-21","cited_by_count":8,"area":null},{"id":"2403.03827","title":"An L-BFGS-B approach for linear and nonlinear system identification under $\\ell_1$ and group-Lasso regularization","created":"2024-03-06","cited_by_count":8,"area":null},{"id":"2403.12732","title":"Tighter Confidence Bounds for Sequential Kernel Regression","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2410.11061","title":"Learning to Optimize for Mixed-Integer Non-linear Programming with Feasibility Guarantees","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2210.14312","title":"JAX-DIPS: Neural bootstrapping of finite discretization methods and application to elliptic problems with discontinuities","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2304.11153","title":"Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2412.09734","title":"MPAX: Mathematical Programming in JAX","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2202.12404","title":"Exploiting Problem Structure in Deep Declarative Networks: Two Case Studies","created":"2022-02-24","cited_by_count":6,"area":null},{"id":"2210.06574","title":"Gaussian Processes on Distributions based on Regularized Optimal Transport","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2306.11895","title":"Learning Elastic Costs to Shape Monge Displacements","created":"2023-06-20","cited_by_count":6,"area":null},{"id":"2409.14611","title":"Secrets of Edge-Informed Contrast Maximization for Event-Based Vision","created":"2024-09-22","cited_by_count":6,"area":null},{"id":"2505.21404","title":"Dual Natural Gradient Descent for Scalable Training of Physics-Informed Neural Networks","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2506.10872","title":"The Gittins Index: A Design Principle for Decision-Making Under Uncertainty","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2510.04951","title":"Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the Constraints","created":"2025-10-06","cited_by_count":6,"area":null},{"id":"2202.12795","title":"Equilibrium Aggregation: Encoding Sets via Optimization","created":"2022-02-25","cited_by_count":5,"area":null},{"id":"2212.07844","title":"Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2406.09882","title":"Harm Mitigation in Recommender Systems under User Preference Dynamics","created":"2024-06-14","cited_by_count":5,"area":null},{"id":"2205.10242","title":"EXODUS: Stable and Efficient Training of Spiking Neural Networks","created":"2022-05-20","cited_by_count":4,"area":null},{"id":"2205.12751","title":"Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2206.01730","title":"On the complexity of nonsmooth automatic differentiation","created":"2022-06-01","cited_by_count":4,"area":null},{"id":"2209.07679","title":"Learning Pair Potentials using Differentiable Simulations","created":"2022-09-16","cited_by_count":4,"area":null},{"id":"2409.03306","title":"Towards training digitally-tied analog blocks via hybrid gradient computation","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2501.17737","title":"Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2505.00793","title":"Scalable Meta-Learning via Mixed-Mode Differentiation","created":"2025-05-01","cited_by_count":4,"area":null},{"id":"2505.20515","title":"Semi-Explicit Neural DAEs: Learning Long-Horizon Dynamical Systems with Algebraic Constraints","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2506.11898","title":"Martingale Posterior Neural Networks for Fast Sequential Decision Making","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2605.01361","title":"Decision-Focused Learning via Tangent-Space Projection of Prediction Error","created":"2026-05-02","cited_by_count":4,"area":null},{"id":"2206.00694","title":"Meta-SysId: A Meta-Learning Approach for Simultaneous Identification and Prediction","created":"2022-06-01","cited_by_count":3,"area":null},{"id":"2206.04663","title":"Provably efficient variational generative modeling of quantum many-body systems via quantum-probabilistic information geometry","created":"2022-06-09","cited_by_count":3,"area":null},{"id":"2212.05908","title":"Instance-Conditional Timescales of Decay for Non-Stationary Learning","created":"2022-12-12","cited_by_count":3,"area":null},{"id":"2305.15042","title":"Test like you Train in Implicit Deep Learning","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2306.05566","title":"Data-Adaptive Probabilistic Likelihood Approximation for Ordinary Differential Equations","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2310.12804","title":"Differentiable Vertex Fitting for Jet Flavour Tagging","created":"2023-10-19","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":"2406.15076","title":"Neural Incremental Data Assimilation","created":"2024-06-21","cited_by_count":3,"area":null},{"id":"2410.23391","title":"Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective","created":"2024-10-30","cited_by_count":3,"area":null},{"id":"2502.19611","title":"PRDP: Progressively Refined Differentiable Physics","created":"2025-02-26","cited_by_count":3,"area":null},{"id":"2512.02494","title":"A Fully First-Order Layer for Differentiable Optimization","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2601.13994","title":"torch-sla: Differentiable Sparse Linear Algebra with Adjoint Solvers and Sparse Tensor Parallelism for PyTorch","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2111.05218","title":"A research framework for writing differentiable PDE discretizations in JAX","created":"2021-11-09","cited_by_count":2,"area":null},{"id":"2212.05987","title":"Selective classification using a robust meta-learning approach","created":"2022-12-12","cited_by_count":2,"area":null},{"id":"2304.05362","title":"MASIL: Towards Maximum Separable Class Representation for Few Shot Class Incremental Learning","created":"2023-04-08","cited_by_count":2,"area":null},{"id":"2312.03807","title":"Achieving ${O}(\\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2403.11687","title":"Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2406.08399","title":"Differentiable Cost-Parameterized Monge Map Estimators","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2412.13200","title":"Forward and Inverse Simulation of Pseudo-Two-Dimensional Model of Lithium-Ion Batteries Using Neural Networks","created":"2024-12-02","cited_by_count":2,"area":null}],"next_cursor":"100"}