120 citations · 429 across the 26 of their papers we have counts for
26 papers
OmniPred: Language Models as Universal Regressors
Xingyou Song, Oscar Li, Chansoo Lee +4
Regression is a powerful tool to accurately predict the outcome metric of a system given a set of parameters, but has traditionally been restricted to methods which are only applic…
Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products
Tamas Sarlos, Xingyou Song, David Woodruff +2
Inspired by fast algorithms in natural language processing, we study low rank approximation in the entrywise transformed setting where we want to find a good rank approximation…
Discovering Adaptable Symbolic Algorithms from Scratch
Stephen Kelly, Daniel S. Park, Xingyou Song +8
Autonomous robots deployed in the real world will need control policies that rapidly adapt to environmental changes. To this end, we propose AutoRobotics-Zero (ARZ), a method based…
Open Source Vizier: Distributed Infrastructure and API for Reliable and Flexible Blackbox Optimization
Xingyou Song, Sagi Perel, Chansoo Lee +2
Vizier is the de-facto blackbox and hyperparameter optimization service across Google, having optimized some of Google's largest products and research efforts. To operate at the sc…
Towards Learning Universal Hyperparameter Optimizers with Transformers
Yutian Chen, Xingyou Song, Chansoo Lee +9
Meta-learning hyperparameter optimization (HPO) algorithms from prior experiments is a promising approach to improve optimization efficiency over objective functions from a similar…
Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
Jack Parker-Holder, Raghu Rajan, Xingyou Song +9
The combination of Reinforcement Learning (RL) with deep learning has led to a series of impressive feats, with many believing (deep) RL provides a path towards generally capable a…
Debiasing a First-order Heuristic for Approximate Bi-level Optimization
Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski +2
Approximate bi-level optimization (ABLO) consists of (outer-level) optimization problems, involving numerical (inner-level) optimization loops. While ABLO has many applications acr…
Differentiable Architecture Search for Reinforcement Learning
Yingjie Miao, Xingyou Song, John D. Co-Reyes +4
In this paper, we investigate the fundamental question: To what extent are gradient-based neural architecture search (NAS) techniques applicable to RL? Using the original DARTS as…
Unlocking Pixels for Reinforcement Learning via Implicit Attention
Krzysztof Marcin Choromanski, Deepali Jain, Wenhao Yu +9
There has recently been significant interest in training reinforcement learning (RL) agents in vision-based environments. This poses many challenges, such as high dimensionality an…
ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder +8
In this paper, we approach the problem of optimizing blackbox functions over large hybrid search spaces consisting of both combinatorial and continuous parameters. We demonstrate t…
Sub-Linear Memory: How to Make Performers SLiM
Valerii Likhosherstov, Krzysztof Choromanski, Jared Davis +2
The Transformer architecture has revolutionized deep learning on sequential data, becoming ubiquitous in state-of-the-art solutions for a wide variety of applications. Yet vanilla…
Rethinking Attention with Performers
Krzysztof Choromanski, Valerii Likhosherstov, David Dohan +10
We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed t…
An Ode to an ODE
Krzysztof Choromanski, Jared Quincy Davis, Valerii Likhosherstov +6
We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the orthogonal group O(d…
UFO-BLO: Unbiased First-Order Bilevel Optimization
Valerii Likhosherstov, Xingyou Song, Krzysztof Choromanski +2
Bilevel optimization (BLO) is a popular approach with many applications including hyperparameter optimization, neural architecture search, adversarial robustness and model-agnostic…
Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers
Krzysztof Choromanski, Valerii Likhosherstov, David Dohan +8
Transformer models have achieved state-of-the-art results across a diverse range of domains. However, concern over the cost of training the attention mechanism to learn complex dep…
Stochastic Flows and Geometric Optimization on the Orthogonal Group
Krzysztof Choromanski, David Cheikhi, Jared Davis +12
We present a new class of stochastic, geometrically-driven optimization algorithms on the orthogonal group and naturally reductive homogeneous manifolds obtained from the ac…
Robotic Table Tennis with Model-Free Reinforcement Learning
Wenbo Gao, Laura Graesser, Krzysztof Choromanski +5
We propose a model-free algorithm for learning efficient policies capable of returning table tennis balls by controlling robot joints at a rate of 100Hz. We demonstrate that evolut…
Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning
Xingyou Song, Yuxiang Yang, Krzysztof Choromanski +4
Learning adaptable policies is crucial for robots to operate autonomously in our complex and quickly changing world. In this work, we present a new meta-learning method that allows…
Observational Overfitting in Reinforcement Learning
Xingyou Song, Yiding Jiang, Stephen Tu +2
A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the…
Gradientless Descent: High-Dimensional Zeroth-Order Optimization
Daniel Golovin, John Karro, Greg Kochanski +3
Zeroth-order optimization is the process of minimizing an objective , given oracle access to evaluations at adaptively chosen inputs . In this paper, we present two simple…
ES-MAML: Simple Hessian-Free Meta Learning
Xingyou Song, Wenbo Gao, Yuxiang Yang +3
We introduce ES-MAML, a new framework for solving the model agnostic meta learning (MAML) problem based on Evolution Strategies (ES). Existing algorithms for MAML are based on poli…
Reinforcement Learning with Chromatic Networks for Compact Architecture Search
Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder +6
We present a neural architecture search algorithm to construct compact reinforcement learning (RL) policies, by combining ENAS and ES in a highly scalable and intuitive way. By def…
An Empirical Study on Hyperparameters and their Interdependence for RL Generalization
Xingyou Song, Yilun Du, Jacob Jackson
Recent results in Reinforcement Learning (RL) have shown that agents with limited training environments are susceptible to a large amount of overfitting across many domains. A key…
The Principle of Unchanged Optimality in Reinforcement Learning Generalization
Alex Irpan, Xingyou Song
Several recent papers have examined generalization in reinforcement learning (RL), by proposing new environments or ways to add noise to existing environments, then benchmarking al…