{"total":45,"rows":[{"id":"2106.04350","title":"Nonsmooth Implicit Differentiation for Machine Learning and Optimization","created":"2021-06-08","cited_by_count":43,"area":null},{"id":"2201.11968","title":"Training invariances and the low-rank phenomenon: beyond linear networks","created":"2022-01-28","cited_by_count":33,"area":null},{"id":"2102.07976","title":"A General Descent Aggregation Framework for Gradient-based Bi-level Optimization","created":"2021-02-16","cited_by_count":28,"area":null},{"id":"2206.00457","title":"Automatic differentiation of nonsmooth iterative algorithms","created":"2022-05-31","cited_by_count":25,"area":null},{"id":"2105.01637","title":"Implicit differentiation for fast hyperparameter selection in non-smooth convex learning","created":"2021-05-04","cited_by_count":22,"area":null},{"id":"2206.06135","title":"Flexible Differentiable Optimization via Model Transformations","created":"2022-06-10","cited_by_count":16,"area":null},{"id":"2308.09858","title":"Tensor-Compressed Back-Propagation-Free Training for (Physics-Informed) Neural Networks","created":"2023-08-18","cited_by_count":12,"area":null},{"id":"2311.18718","title":"The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2208.08772","title":"Lifted Bregman Training of Neural Networks","created":"2022-08-18","cited_by_count":10,"area":null},{"id":"2108.02072","title":"Stochastic Subgradient Descent Escapes Active Strict Saddles on Weakly Convex Functions","created":"2021-08-04","cited_by_count":9,"area":null},{"id":"2503.01660","title":"Non-convergence to the optimal risk for Adam and stochastic gradient descent optimization in the training of deep neural networks","created":"2025-03-03","cited_by_count":6,"area":null},{"id":"2109.00530","title":"A Gradient Sampling Algorithm for Stratified Maps with Applications to Topological Data Analysis","created":"2021-09-01","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":"2310.08858","title":"Adam-family Methods with Decoupled Weight Decay in Deep Learning","created":"2023-10-13","cited_by_count":5,"area":null},{"id":"2411.05873","title":"Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach","created":"2024-11-07","cited_by_count":5,"area":null},{"id":"2101.00699","title":"The structure of conservative gradient fields","created":"2021-01-03","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":"2208.03107","title":"Fixed-Point Automatic Differentiation of Forward--Backward Splitting Algorithms for Partly Smooth Functions","created":"2022-08-05","cited_by_count":4,"area":null},{"id":"2103.03570","title":"Second-order step-size tuning of SGD for non-convex optimization","created":"2021-03-05","cited_by_count":3,"area":null},{"id":"2301.13370","title":"On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters","created":"2023-01-31","cited_by_count":3,"area":null},{"id":"2302.10636","title":"$\\omega$PAP Spaces: Reasoning Denotationally About Higher-Order, Recursive Probabilistic and Differentiable Programs","created":"2023-02-21","cited_by_count":3,"area":null},{"id":"2305.16901","title":"Generalizing Adam to Manifolds for Efficiently Training Transformers","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2307.10053","title":"Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization","created":"2023-07-19","cited_by_count":3,"area":null},{"id":"2509.18025","title":"Deep Learning as the Disciplined Construction of Tame Objects","created":"2025-09-22","cited_by_count":3,"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":"2404.09438","title":"Developing Lagrangian-based Methods for Nonsmooth Nonconvex Optimization","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2505.11370","title":"Understanding Nonlinear Implicit Bias via Region Counts in Input Space","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2607.16183","title":"A Blueprint for Equilibrium-Based Differentiable Continuous-Variable Thermodynamic Computing","created":"2026-07-17","cited_by_count":2,"area":null},{"id":"2201.03819","title":"Path differentiability of ODE flows","created":"2022-01-11","cited_by_count":1,"area":null},{"id":"2211.04655","title":"Perturbed Iterate SGD for Lipschitz Continuous Loss Functions with Numerical Error and Adaptive Step Sizes","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2305.07546","title":"Understanding Automatic Differentiation Pitfalls","created":"2023-05-12","cited_by_count":1,"area":null},{"id":"2306.00088","title":"Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2311.13544","title":"Piecewise Polynomial Regression of Tame Functions via Integer Programming","created":"2023-11-22","cited_by_count":1,"area":null},{"id":"2403.11565","title":"Convergence of Decentralized Stochastic Subgradient-based Methods for Nonsmooth Nonconvex functions","created":"2024-03-18","cited_by_count":1,"area":null},{"id":"2410.15923","title":"Automatic Differentiation of Optimization Algorithms with Time-Varying Updates","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2410.22065","title":"Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient","created":"2024-10-29","cited_by_count":1,"area":null},{"id":"2509.15368","title":"Stochastic Sample Approximations of (Local) Moduli of Continuity","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2605.24477","title":"The Normalized Maximum Likelihood for Regular Non-Smooth Models: Measure-Theoretic Foundations and Geometric Sampling","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2106.12915","title":"Numerical influence of ReLU'(0) on backpropagation","created":"2021-06-23","cited_by_count":0,"area":null},{"id":"2401.02736","title":"On the numerical reliability of nonsmooth autodiff: a MaxPool case study","created":"2024-01-05","cited_by_count":0,"area":null},{"id":"2602.07581","title":"$\\partial$CBDs: Differentiable Causal Block Diagrams","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2605.04722","title":"Dual Certified White-Box Inference for Input Convex Neural Networks","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2607.01755","title":"Decentralized Stochastic Subgradient-type Methods with Communication Compression for Nonsmooth Nonconvex Optimization","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.30960","title":"Branch Geometry and Finite-Radius Sensitivity of Hard-ReLU Training","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.38786","title":"Same Loss, Different Gradients","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}