Portrait de Elliot Paquette

Elliot Paquette

Membre académique associé
Professeur agrégé, McGill University, Département de mathématiques et de statistique
Sujets de recherche
Optimisation
Théorie de l'apprentissage automatique
Site web
Google Scholar
X

Publications

Hitting the High-dimensional notes: an ODE for SGD learning dynamics on GLMs and multi-index models
Elizabeth Collins-Woodfin
Courtney Paquette
Elliot Paquette
INBAR SEROUSSI
We analyze the dynamics of streaming stochastic gradient descent (SGD) in the high-dimensional limit when applied to generalized linear mode… (voir plus)ls and multi-index models (e.g. logistic regression, phase retrieval) with general data-covariance. In particular, we demonstrate a deterministic equivalent of SGD in the form of a system of ordinary differential equations that describes a wide class of statistics, such as the risk and other measures of sub-optimality. This equivalence holds with overwhelming probability when the model parameter count grows proportionally to the number of data. This framework allows us to obtain learning rate thresholds for stability of SGD as well as convergence guarantees. In addition to the deterministic equivalent, we introduce an SDE with a simplified diffusion coefficient (homogenized SGD) which allows us to analyze the dynamics of general statistics of SGD iterates. Finally, we illustrate this theory on some standard examples and show numerical simulations which give an excellent match to the theory.
2023-08-16
ArXiv (prépublication)
doi.org
arxiv.org
Homogenization of SGD in high-dimensions: Exact dynamics and generalization properties
Courtney Paquette
Elliot Paquette
Ben Adlam
Jeffrey Pennington
2022-05-13
ArXiv (prépublication)
arxiv.org
arxiv.org
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions
Courtney Paquette
Elliot Paquette
Ben Adlam
Jeffrey Pennington
Stochastic gradient descent (SGD) is a pillar of modern machine learning, serving as the go-to optimization algorithm for a diverse array of… (voir plus) problems. While the empirical success of SGD is often attributed to its computational efficiency and favorable generalization behavior, neither effect is well understood and disentangling them remains an open problem. Even in the simple setting of convex quadratic problems, worst-case analyses give an asymptotic convergence rate for SGD that is no better than full-batch gradient descent (GD), and the purported implicit regularization effects of SGD lack a precise explanation. In this work, we study the dynamics of multi-pass SGD on high-dimensional convex quadratics and establish an asymptotic equivalence to a stochastic differential equation, which we call homogenized stochastic gradient descent (HSGD), whose solutions we characterize explicitly in terms of a Volterra integral equation. These results yield precise formulas for the learning and risk trajectories, which reveal a mechanism of implicit conditioning that explains the efficiency of SGD relative to GD. We also prove that the noise from SGD negatively impacts generalization performance, ruling out the possibility of any type of implicit regularization in this context. Finally, we show how to adapt the HSGD formalism to include streaming SGD, which allows us to produce an exact prediction for the excess risk of multi-pass SGD relative to that of streaming SGD (bootstrap risk).
2021-12-31
Advances in Neural Information Processing Systems 35 (NeurIPS 2022) (publié)
doi.org
openreview.net
Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions
Kiwon Lee
Andrew N. Cheng
Courtney Paquette
Elliot Paquette
We analyze the dynamics of large batch stochastic gradient descent with momentum (SGD+M) on the least squares problem when both the number o… (voir plus)f samples and dimensions are large. In this setting, we show that the dynamics of SGD+M converge to a deterministic discrete Volterra equation as dimension increases, which we analyze. We identify a stability measurement, the implicit conditioning ratio (ICR), which regulates the ability of SGD+M to accelerate the algorithm. When the batch size exceeds this ICR, SGD+M converges linearly at a rate of
2021-12-31
Advances in Neural Information Processing Systems 35 (NeurIPS 2022) (publié)
doi.org
openreview.net