gradient computation

Making Scalable Meta Learning Practical NeurIPS 2023 On quantum backpropagation, information reuse, and cheating measurement collapse NeurIPS 2023 On the Correctness of Automatic Differentiation for Neural Networks with Machine-Representable Parameters ICML 2023 An In-depth Study of Stochastic Backpropagation NeurIPS 2022 A Unified Framework for Implicit Sinkhorn Differentiation CVPR 2022 Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations NeurIPS 2022 Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models CVPR 2022 Symplectic Adjoint Method for Exact Gradient of Neural ODE with Minimal Memory NeurIPS 2021 Understanding and Mitigating Exploding Inverses in Invertible Neural Networks AISTATS 2021 Automatic Differentiation of Sketched Regression AISTATS 2020 Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization NeurIPS 2020 Scalable Gradients for Stochastic Differential Equations AISTATS 2020 Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks NeurIPS 2020 An Investigation into On-Device Personalization of End-to-End Automatic Speech Recognition Models Interspeech 2019 AutoAssist: A Framework to Accelerate Training of Deep Neural Networks NeurIPS 2019 Differentiable Cloth Simulation for Inverse Problems NeurIPS 2019 Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems AISTATS 2018 Automatic Differentiation in Machine Learning: a Survey JMLR 2018 Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance NeurIPS 2018 Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses NeurIPS 2018 Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks NeurIPS 2018 Provably Correct Automatic Sub-Differentiation for Qualified Programs NeurIPS 2018 Tangent: Automatic differentiation using source-code transformation for dynamically typed array programming NeurIPS 2018 Training Deep Neural Networks with 8-bit Floating Point Numbers NeurIPS 2018 The Reversible Residual Network: Backpropagation Without Storing Activations NeurIPS 2017