
-
Acceleration via Fractal Learning Rate Schedules
When balancing the practical tradeoffs of iterative methods for large-sc...
read it
-
Deluca – A Differentiable Control Library: Environments, Methods, and Benchmarking
We present an open-source library of natively differentiable physics and...
read it
-
Machine Learning for Mechanical Ventilation Control
We consider the problem of controlling an invasive mechanical ventilator...
read it
-
Stochastic Optimization with Laggard Data Pipelines
State-of-the-art optimization is steadily shifting towards massively par...
read it
-
Disentangling Adaptive Gradient Methods from Learning Rates
We investigate several confounding factors in the evaluation of optimiza...
read it
-
No-Regret Prediction in Marginally Stable Systems
We consider the problem of online prediction in a marginally stable line...
read it
-
Calibration, Entropy Rates, and Memory in Language Models
Building accurate language models that capture meaningful long-term depe...
read it
-
Robust guarantees for learning an autoregressive filter
The optimal predictor for a linear dynamical system (with hidden state a...
read it
-
Extreme Tensoring for Low-Memory Preconditioning
State-of-the-art models are now trained with billions of parameters, rea...
read it
-
The Case for Full-Matrix Adaptive Regularization
Adaptive regularization methods come in diagonal and full-matrix variant...
read it
-
Spectral Filtering for General Linear Dynamical Systems
We give a polynomial-time algorithm for learning latent-state linear dyn...
read it
-
Learning Linear Dynamical Systems via Spectral Filtering
We present an efficient and practical algorithm for the online predictio...
read it
-
Not-So-Random Features
We propose a principled method for kernel learning, which relies on a Fo...
read it
-
Efficient Regret Minimization in Non-Convex Games
We consider regret minimization in repeated games with non-convex loss f...
read it