Cyril Zhang

is this you? claim profile

0 followers
Princeton University

Acceleration via Fractal Learning Rate Schedules

When balancing the practical tradeoffs of iterative methods for large-sc...
03/01/2021 ∙ by Naman Agarwal, et al. ∙ 4 ∙ share

read it
Deluca – A Differentiable Control Library: Environments, Methods, and Benchmarking

We present an open-source library of natively differentiable physics and...
02/19/2021 ∙ by Paula Gradu, et al. ∙ 30 ∙ share

read it
Machine Learning for Mechanical Ventilation Control

We consider the problem of controlling an invasive mechanical ventilator...
02/12/2021 ∙ by Daniel Suo, et al. ∙ 14 ∙ share

read it
Stochastic Optimization with Laggard Data Pipelines

State-of-the-art optimization is steadily shifting towards massively par...
10/26/2020 ∙ by Naman Agarwal, et al. ∙ 20 ∙ share

read it
Disentangling Adaptive Gradient Methods from Learning Rates

We investigate several confounding factors in the evaluation of optimiza...
02/26/2020 ∙ by Naman Agarwal, et al. ∙ 6 ∙ share

read it
No-Regret Prediction in Marginally Stable Systems

We consider the problem of online prediction in a marginally stable line...
02/06/2020 ∙ by Udaya Ghai, et al. ∙ 0 ∙ share

read it
Calibration, Entropy Rates, and Memory in Language Models

Building accurate language models that capture meaningful long-term depe...
06/11/2019 ∙ by Mark Braverman, et al. ∙ 1 ∙ share

read it
Robust guarantees for learning an autoregressive filter

The optimal predictor for a linear dynamical system (with hidden state a...
05/23/2019 ∙ by Holden Lee, et al. ∙ 0 ∙ share

read it
Extreme Tensoring for Low-Memory Preconditioning

State-of-the-art models are now trained with billions of parameters, rea...
02/12/2019 ∙ by Xinyi Chen, et al. ∙ 0 ∙ share

read it
The Case for Full-Matrix Adaptive Regularization

Adaptive regularization methods come in diagonal and full-matrix variant...
06/08/2018 ∙ by Naman Agarwal, et al. ∙ 0 ∙ share

read it
Spectral Filtering for General Linear Dynamical Systems

We give a polynomial-time algorithm for learning latent-state linear dyn...
02/12/2018 ∙ by Elad Hazan, et al. ∙ 0 ∙ share

read it
Learning Linear Dynamical Systems via Spectral Filtering

We present an efficient and practical algorithm for the online predictio...
11/02/2017 ∙ by Elad Hazan, et al. ∙ 0 ∙ share

read it
Not-So-Random Features

We propose a principled method for kernel learning, which relies on a Fo...
10/27/2017 ∙ by Brian Bullins, et al. ∙ 0 ∙ share

read it
Efficient Regret Minimization in Non-Convex Games

We consider regret minimization in repeated games with non-convex loss f...
07/31/2017 ∙ by Elad Hazan, et al. ∙ 0 ∙ share

read it

Cyril Zhang

Featured Co-authors

Yi Zhang

Sham M. Kakade

Elad Hazan

Tomer Koren

Kunal Talwar

Karthik Narasimhan

Karan Singh

Naman Agarwal

Anirudha Majumdar

Surbhi Goel

Mark Braverman

Acceleration via Fractal Learning Rate Schedules

Deluca – A Differentiable Control Library: Environments, Methods, and Benchmarking

Machine Learning for Mechanical Ventilation Control

Stochastic Optimization with Laggard Data Pipelines

Disentangling Adaptive Gradient Methods from Learning Rates

No-Regret Prediction in Marginally Stable Systems

Calibration, Entropy Rates, and Memory in Language Models

Robust guarantees for learning an autoregressive filter

Extreme Tensoring for Low-Memory Preconditioning

The Case for Full-Matrix Adaptive Regularization

Spectral Filtering for General Linear Dynamical Systems

Learning Linear Dynamical Systems via Spectral Filtering

Not-So-Random Features

Efficient Regret Minimization in Non-Convex Games