
Unlocking Pixels for Reinforcement Learning via Implicit Attention
There has recently been significant interest in training reinforcement l...
read it

ESENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning
We introduce ESENAS, a simple neural architecture search (NAS) algorith...
read it

MLGO: a Machine Learning Guided Compiler Optimizations Framework
Leveraging machinelearning (ML) techniques for compiler optimizations h...
read it

SubLinear Memory: How to Make Performers SLiM
The Transformer architecture has revolutionized deep learning on sequent...
read it

Rethinking Attention with Performers
We introduce Performers, Transformer architectures which can estimate re...
read it

On Optimism in ModelBased Reinforcement Learning
The principle of optimism in the face of uncertainty is prevalent throug...
read it

An Ode to an ODE
We present a new paradigm for Neural ODE algorithms, calledODEtoODE, whe...
read it

Online Hyperparameter Tuning in Offpolicy Learning via Evolutionary Strategies
Offpolicy learning algorithms have been known to be sensitive to the ch...
read it

UFOBLO: Unbiased FirstOrder Bilevel Optimization
Bilevel optimization (BLO) is a popular approach with many applications ...
read it

Masked Language Modeling for Proteins via Linearly Scalable LongContext Transformers
Transformer models have achieved stateoftheart results across a diver...
read it

Demystifying Orthogonal Monte Carlo and Beyond
Orthogonal Monte Carlo (OMC) is a very effective sampling algorithm impo...
read it

Time Dependence in NonAutonomous Neural ODEs
Neural Ordinary Differential Equations (ODEs) are elegant reinterpretati...
read it

CWY Parametrization for Scalable Learning of Orthogonal and Stiefel Matrices
In this paper we propose a new approach for optimization over orthogonal...
read it

Robotic Table Tennis with ModelFree Reinforcement Learning
We propose a modelfree algorithm for learning efficient policies capabl...
read it

Stochastic Flows and Geometric Optimization on the Orthogonal Group
We present a new class of stochastic, geometricallydriven optimization ...
read it

Rapidly Adaptable Legged Robots via Evolutionary MetaLearning
Learning adaptable policies is crucial for robots to operate autonomousl...
read it

Ready Policy One: World Building Through Active Learning
ModelBased Reinforcement Learning (MBRL) offers a promising direction f...
read it

Effective Diversity in PopulationBased Reinforcement Learning
Maintaining a population of solutions has been shown to increase explora...
read it

ESMAML: Simple HessianFree Meta Learning
We introduce ESMAML, a new framework for solving the model agnostic met...
read it

Reinforcement Learning with Chromatic Networks
We present a new algorithm for finding compact neural networks encoding ...
read it

Wasserstein Reinforcement Learning
We propose behaviordriven optimization via Wasserstein distances (WDs) ...
read it

Variance Reduction for Evolution Strategies via Structured Control Variates
Evolution Strategies (ES) are a powerful class of blackbox optimization ...
read it

Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes
We propose a new class of structured methods for Monte Carlo (MC) sampli...
read it

Linear interpolation gives better gradients than Gaussian smoothing in derivativefree optimization
In this paper, we consider derivative free optimization problems, where ...
read it

Orthogonal Estimation of Wasserstein Distances
Wasserstein distances are increasingly used in a wide variety of applica...
read it

Adaptive SampleEfficient Blackbox Optimization via ESactive Subspaces
We present a new algorithm ASEBO for conducting optimization of highdim...
read it

When random search is not enough: SampleEfficient and NoiseRobust Blackbox Optimization of RL Policies
Interest in derivativefree optimization (DFO) and "evolutionary strateg...
read it

Optimizing Simulations with NoiseTolerant Structured Exploration
We propose a simple dropin noisetolerant replacement for the standard ...
read it

Structured Evolution with Compact Architectures for Scalable Policy Optimization
We present a new method of blackbox optimization via gradient approximat...
read it

On the Needs for Rotations in Hypercubic Quantization Hashing
The aim of this paper is to endow the wellknown family of hypercubic qu...
read it

Manifold Regularization for Kernelized LSTD
Policy evaluation or value function or Qfunction approximation is a key...
read it

Explaining How a Deep Neural Network Trained with EndtoEnd Learning Steers a Car
As part of a complete software stack for autonomous driving, NVIDIA has ...
read it

The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings
We examine a class of embeddings based on structured random matrices wit...
read it

VisualBackProp: efficient visualization of CNNs
This paper proposes a new method, that we call VisualBackProp, for visua...
read it

Orthogonal Random Features
We present an intriguing discovery related to Random Fourier Features: i...
read it

Recycling Randomness with Structure for Sublinear time Kernel Expansions
We propose a scheme for recycling Gaussian random vectors into structure...
read it

TripleSpin  a generic compact paradigm for fast machine learning computations
We present a generic compact computational framework relying on structur...
read it

Fast nonlinear embeddings via structured matrices
We present a new paradigm for speeding up randomized computations of sev...
read it

Binary embeddings with structured hashed projections
We consider the hashing mechanism for constructing binary embeddings, th...
read it

Quantization based Fast Inner Product Search
We propose a quantization based approach for fast approximate Maximum In...
read it

Fast Online Clustering with Randomized Skeleton Sets
We present a new fast online clustering algorithm that reliably recovers...
read it

Differentially and nondifferentiallyprivate random decision trees
We consider supervised learning with random decision trees, where the tr...
read it

On Learning from Label Proportions
Learning from Label Proportions (LLP) is a learning setting, where the t...
read it
Krzysztof Choromanski
is this you? claim profile
Adjunct Assistant Professor of Industrial Engineering and Operations Research at Columbia University in the City of New York since 2015, Research Scientist at Google Brain Robotics since 2013, Doctoral student at Columbia University from 20092013, Pregel Team member  distributed computations on large graphs at Google Inc. 2012, master degree student (mathematics and computer science  double degree program) at University of Warsaw from 20052009, summer intern at IBM 2008.