22 citations · 79 across the 22 of their papers we have counts for
4 papers · 1 filter
Spectral State Space Models
Naman Agarwal, Daniel Suo, Xinyi Chen +1
This paper studies sequence modeling for prediction tasks with long range dependencies. We propose a new formulation for state space models (SSMs) based on learning linear dynamica…
Playing Large Games with Oracles and AI Debate
Xinyi Chen, Angelica Chen, Dean Foster +1
We consider regret minimization in repeated games with a very large number of actions. Such games are inherent in the setting of AI Safety via Debate \cite{irving2018ai}, and more…
Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions
Vladimir Feinberg, Xinyi Chen, Y. Jennifer Sun +2
Adaptive regularization methods that exploit more than the diagonal entries exhibit state of the art performance for many tasks, but can be prohibitive in terms of memory and runni…
A Nonstochastic Control Approach to Optimization
Xinyi Chen, Elad Hazan
Selecting the best hyperparameters for a particular optimization instance, such as the learning rate and momentum, is an important but nonconvex problem. As a result, iterative opt…