Courtney Paquette

28 papers A* 8A 2Journal 18
YearRankTypeTitle / Venue / Authors
2026 J jnl
Logarithmic-time Schedules for Scaling Language Models with Momentum.
CoRR
Damien Ferbach, Courtney Paquette, Gauthier Gidel, Katie Everett, Elliot Paquette
2026 J jnl
Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems.
SIAM J. Optim.
Tomás González, Cristóbal Guzmán, Courtney Paquette
2025 J jnl
Dimension-adapted Momentum Outscales SGD.
CoRR
Damien Ferbach, Katie Everett, Gauthier Gidel, Elliot Paquette, Courtney Paquette
2025 J jnl
Homogenization of SGD in high-dimensions: exact dynamics and generalization properties.
Math. Program.
Courtney Paquette, Elliot Paquette, Ben Adlam, Jeffrey Pennington
2025 A conf
Implicit Diffusion: Efficient optimization through stochastic sampling.
AISTATS
Pierre Marion, Anna Korba, Peter L. Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet
2025 J jnl
Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models.
CoRR
Alexander B. Atanasov, Blake Bordelon, Jacob A. Zavatone-Veth, Courtney Paquette, Cengiz Pehlevan
2024 A* conf
4+3 Phases of Compute-Optimal Neural Scaling Laws.
NeurIPS
Elliot Paquette, Courtney Paquette, Lechao Xiao, Jeffrey Pennington
2024 J jnl
4+3 Phases of Compute-Optimal Neural Scaling Laws.
CoRR
Elliot Paquette, Courtney Paquette, Lechao Xiao, Jeffrey Pennington
2024 J jnl
Implicit Diffusion: Efficient Optimization through Stochastic Sampling.
CoRR
Pierre Marion, Anna Korba, Peter L. Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet
2024 A* conf
Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems extended abstract.
COLT
Tomás González, Cristóbal Guzmán, Courtney Paquette
2024 J jnl
Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems.
CoRR
Tomás González, Cristóbal Guzmán, Courtney Paquette
2024 A* conf
The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms.
NeurIPS
Elizabeth Collins-Woodfin, Inbar Seroussi, Begoña García Malaxechebarría, Andrew W. Mackenzie, Elliot Paquette, Courtney Paquette
2023 J jnl
Halting Time is Predictable for Large Models: A Universality Property and Average-Case Analysis.
Found. Comput. Math.
Courtney Paquette, Bart van Merriënboer, Elliot Paquette, Fabian Pedregosa
2023 J jnl
Hitting the High-Dimensional Notes: An ODE for SGD learning dynamics on GLMs and multi-index models.
CoRR
Elizabeth Collins-Woodfin, Courtney Paquette, Elliot Paquette, Inbar Seroussi
2022 A* conf
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions.
NeurIPS
Courtney Paquette, Elliot Paquette, Ben Adlam, Jeffrey Pennington
2022 J jnl
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions.
CoRR
Courtney Paquette, Elliot Paquette, Ben Adlam, Jeffrey Pennington
2022 J jnl
Only Tails Matter: Average-Case Universality and Robustness in the Convex Regime.
CoRR
Leonardo Cunha, Gauthier Gidel, Fabian Pedregosa, Damien Scieur, Courtney Paquette
2022 A* conf
Only tails matter: Average-Case Universality and Robustness in the Convex Regime.
ICML
Leonardo Cunha, Gauthier Gidel, Fabian Pedregosa, Damien Scieur, Courtney Paquette
2022 A* conf
Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions.
NeurIPS
Kiwon Lee, Andrew N. Cheng, Elliot Paquette, Courtney Paquette
2022 J jnl
Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions.
CoRR
Kiwon Lee, Andrew N. Cheng, Courtney Paquette, Elliot Paquette
2021 A* conf
Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models.
NeurIPS
Courtney Paquette, Elliot Paquette
2021 J jnl
Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models.
CoRR
Courtney Paquette, Elliot Paquette
2021 A* conf
SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality.
COLT
Courtney Paquette, Kiwon Lee, Fabian Pedregosa, Elliot Paquette
2021 J jnl
SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality.
CoRR
Courtney Paquette, Kiwon Lee, Fabian Pedregosa, Elliot Paquette
2020 J jnl
A Stochastic Line Search Method with Expected Complexity Analysis.
SIAM J. Optim.
Courtney Paquette, Katya Scheinberg
2019 J jnl
Efficiency of minimizing compositions of convex functions and smooth maps.
Math. Program.
Dmitriy Drusvyatskiy, Courtney Paquette
2018 A conf
Catalyst for Gradient-based Nonconvex Optimization.
AISTATS
Courtney Paquette, Hongzhou Lin, Dmitriy Drusvyatskiy, Julien Mairal, Zaïd Harchaoui
2018 J jnl
Subgradient Methods for Sharp Weakly Convex Functions.
J. Optim. Theory Appl.
Damek Davis, Dmitriy Drusvyatskiy, Kellie J. MacPhee, Courtney Paquette