DELTA-STN: EFFICIENT BILEVEL OPTIMIZATION FOR NEURAL NETWORKS USING STRUCTURED RESPONSE JACOBIANS

von Bae, Juhan
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 26 of 27 (2021)

Regularized linear autoencoders recover the principal components, eventually

von Bao, Xuchan
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 9 of 27 (2021)

Proximal Learning With Opponent-Learning Awareness

von Zhao, Stephen
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 34 of 50 (2023)

Amortized Proximal Optimization

von Bae, Juhan
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 12 of 50 (2023)

Differentiable Annealed Importance Sampling and the Perils of Gradient Noise

von Zhang, Guodong
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 23 of 36 (2022)

If Influence Functions are the Answer, Then What is the Question?

von Bae, Juhan
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 24 of 50 (2023)

SCALABLE VARIATIONAL GAUSSIAN PROCESSES VIA HARMONIC KERNEL DECOMPOSITION

von SUN, SHENGYANG
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 13 of 16 (2022)

On Implicit Bias in Overparameterized Bilevel Optimization

von Vicol, Paul
Veröffentlicht in International Conference on Machine Learning (39. : 2022 : Baltimore, Md.; Online) International Conference on Machine Learning (ICML 2022) ; Part 27 of 33 (2023)

LIME: LEARNING INDUCTIVE BIAS FOR PRIMITIVES OF MATHEMATICAL REASONING

von WU, YUHUAI
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 14 of 16 (2022)

WHICH ALGORITHMIC CHOICES MATTER AT WHICH BATCH SIZES? INSIGHTS FROM A NOISY QUADRATIC MODEL

von Zhang, Guodong
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 11 of 20 (2020)

Path Independent Equilibrium Models Can Better Exploit Test-Time Computation

von Anil, Cem
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 11 of 50 (2023)