Courtney Paquette
Courtney Paquette
Google Research, Brain Team
Zweryfikowany adres z u.washington.edu - Strona główna
Cytowane przez
Cytowane przez
Efficiency of minimizing compositions of convex functions and smooth maps
D Drusvyatskiy, C Paquette
Mathematical Programming 178, 503-558, 2019
Subgradient methods for sharp weakly convex functions
D Davis, D Drusvyatskiy, KJ MacPhee, C Paquette
Journal of Optimization Theory and Applications 179, 962-982, 2018
The nonsmooth landscape of phase retrieval
D Davis, D Drusvyatskiy, C Paquette
IMA Journal of Numerical Analysis 40 (4), 2652-2695, 2020
A stochastic line search method with expected complexity analysis
C Paquette, K Scheinberg
SIAM Journal on Optimization 30 (1), 349-376, 2020
Catalyst for gradient-based nonconvex optimization
C Paquette, H Lin, D Drusvyatskiy, J Mairal, Z Harchaoui
International Conference on Artificial Intelligence and Statistics, 613-622, 2018
A stochastic line search method with convergence rate analysis
C Paquette, K Scheinberg
arXiv preprint arXiv:1807.07994, 2018
Catalyst acceleration for gradient-based non-convex optimization
C Paquette, H Lin, D Drusvyatskiy, J Mairal, Z Harchaoui
arXiv preprint arXiv:1703.10993, 2017
Sgd in the large: Average-case analysis, asymptotics, and stepsize criticality
C Paquette, K Lee, F Pedregosa, E Paquette
Conference on Learning Theory, 3548-3626, 2021
Halting time is predictable for large models: A universality property and average-case analysis
C Paquette, B van Merriënboer, E Paquette, F Pedregosa
Foundations of Computational Mathematics 23 (2), 597-673, 2023
Variational analysis of spectral functions simplified
D Drusvyatskiy, C Kempton
arXiv preprint arXiv:1506.05170, 2015
Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties
C Paquette, E Paquette, B Adlam, J Pennington
arXiv preprint arXiv:2205.07069, 2022
Dynamics of stochastic momentum methods on large-scale, quadratic models
C Paquette, E Paquette
Advances in Neural Information Processing Systems 34, 9229-9240, 2021
Implicit regularization or implicit conditioning? exact risk trajectories of sgd in high dimensions
C Paquette, E Paquette, B Adlam, J Pennington
Advances in Neural Information Processing Systems 35, 35984-35999, 2022
Trajectory of mini-batch momentum: batch size saturation and convergence in high dimensions
K Lee, A Cheng, E Paquette, C Paquette
Advances in Neural Information Processing Systems 35, 36944-36957, 2022
Hitting the high-dimensional notes: An ode for sgd learning dynamics on glms and multi-index models
E Collins-Woodfin, C Paquette, E Paquette, I Seroussi
arXiv preprint arXiv:2308.08977, 2023
Only tails matter: Average-case universality and robustness in the convex regime
L Cunha, G Gidel, F Pedregosa, D Scieur, C Paquette
International Conference on Machine Learning, 4474-4491, 2022
4+ 3 Phases of Compute-Optimal Neural Scaling Laws
E Paquette, C Paquette, L Xiao, J Pennington
arXiv preprint arXiv:2405.15074, 2024
Potential-based analyses of first-order methods for constrained and composite optimization
C Paquette, S Vavasis
arXiv preprint arXiv:1903.08497, 2019
Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems
T González, C Guzmán, C Paquette
arXiv preprint arXiv:2403.02912, 2024
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
P Marion, A Korba, P Bartlett, M Blondel, V De Bortoli, A Doucet, ...
arXiv preprint arXiv:2402.05468, 2024
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20