Krzysztof Choromanski

Orcid: 0000-0003-3626-414X

Affiliations:
  • Columbia University, Department of Industrial Engineering and Operations Research


According to our database1, Krzysztof Choromanski authored at least 117 papers between 2012 and 2023.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2023
PolyViT: Co-training Vision Transformers on Images, Videos and Audio.
Trans. Mach. Learn. Res., 2023

SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention.
CoRR, 2023

Scalable Neural Network Kernels.
CoRR, 2023

Universal Graph Random Features.
CoRR, 2023

Repelling Random Walks.
CoRR, 2023

Augmenting conformers with structured state space models for online speech recognition.
CoRR, 2023

Robotic Table Tennis: A Case Study into a High Speed Learning System.
CoRR, 2023

Practical Conformer: Optimizing size, speed and flops of Conformer for on-Device and cloud ASR.
CoRR, 2023

Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers.
CoRR, 2023

FAVOR#: Sharp Attention Kernel Approximations via New Classes of Positive Random Features.
CoRR, 2023


Quasi-Monte Carlo Graph Random Features.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Mnemosyne: Learning to Train Transformers with Transformers.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Agile Catching with Whole-Body MPC and Blackbox Policy Learning.
Proceedings of the Learning for Dynamics and Control Conference, 2023

Simplex Random Features.
Proceedings of the International Conference on Machine Learning, 2023


Taming graph kernels with random features.
Proceedings of the International Conference on Machine Learning, 2023

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language.
Proceedings of the Eleventh International Conference on Learning Representations, 2023


On the Expressive Flexibility of Self-Attention Matrices.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimization.
Found. Comput. Math., 2022

Tournaments and the strong Erdős-Hajnal Property.
Eur. J. Comb., 2022

Automated Deep Aberration Detection from Chromosome Karyotype Images.
CoRR, 2022

Multiple View Performers for Shape Completion.
CoRR, 2022

Implicit Two-Tower Policies.
CoRR, 2022

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language.
CoRR, 2022

Chefs' Random Tables: Non-Trigonometric Random Features.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers.
Proceedings of the International Conference on Machine Learning, 2022

Hybrid Random Features.
Proceedings of the Tenth International Conference on Learning Representations, 2022


Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation.
Proceedings of the Conference on Robot Learning, 2022

i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops.
Proceedings of the Conference on Robot Learning, 2022

2021
PolyViT: Co-training Vision Transformers on Images, Videos and Audio.
CoRR, 2021

Graph Kernel Attention Transformers.
CoRR, 2021

On the Expressive Power of Self-Attention Matrices.
CoRR, 2021

Unlocking Pixels for Reinforcement Learning via Implicit Attention.
CoRR, 2021

ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning.
CoRR, 2021

MLGO: a Machine Learning Guided Compiler Optimizations Framework.
CoRR, 2021

Towards tractable optimism in model-based reinforcement learning.
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

Sub-Linear Memory: How to Make Performers SLiM.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Debiasing a First-order Heuristic for Approximate Bi-level Optimization.
Proceedings of the 38th International Conference on Machine Learning, 2021

Catformer: Designing Stable Transformers via Sensitivity Analysis.
Proceedings of the 38th International Conference on Machine Learning, 2021

Rethinking Attention with Performers.
Proceedings of the 9th International Conference on Learning Representations, 2021

CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020
On Optimism in Model-Based Reinforcement Learning.
CoRR, 2020

An Ode to an ODE.
CoRR, 2020

Online Hyper-parameter Tuning in Off-policy Learning via Evolutionary Strategies.
CoRR, 2020

UFO-BLO: Unbiased First-Order Bilevel Optimization.
CoRR, 2020

Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers.
CoRR, 2020

Time Dependence in Non-Autonomous Neural ODEs.
CoRR, 2020

CWY Parametrization for Scalable Learning of Orthogonal and Stiefel Matrices.
CoRR, 2020

Effective Diversity in Population Based Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Demystifying Orthogonal Monte Carlo and Beyond.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Ode to an ODE.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020

Robotic Table Tennis with Model-Free Reinforcement Learning.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020

Unsupervised Anomaly Detection for Self-flying Delivery Drones.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

Learning to Score Behaviors for Guided Policy Optimization.
Proceedings of the 37th International Conference on Machine Learning, 2020

Stochastic Flows and Geometric Optimization on the Orthogonal Group.
Proceedings of the 37th International Conference on Machine Learning, 2020

Ready Policy One: World Building Through Active Learning.
Proceedings of the 37th International Conference on Machine Learning, 2020

ES-MAML: Simple Hessian-Free Meta Learning.
Proceedings of the 8th International Conference on Learning Representations, 2020

Variance Reduction for Evolution Strategies via Structured Control Variates.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Practical Nonisotropic Monte Carlo Sampling in High Dimensions via Determinantal Point Processes.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019
On the Erdős-Hajnal conjecture for six-vertex tournaments.
Eur. J. Comb., 2019

Reinforcement Learning with Chromatic Networks.
CoRR, 2019

Wasserstein Reinforcement Learning.
CoRR, 2019

Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes.
CoRR, 2019

Adaptive Sample-Efficient Blackbox Optimization via ES-active Subspaces.
CoRR, 2019

When random search is not enough: Sample-Efficient and Noise-Robust Blackbox Optimization of RL Policies.
CoRR, 2019

From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Unifying Orthogonal Monte Carlo Methods.
Proceedings of the 36th International Conference on Machine Learning, 2019

Provably Robust Blackbox Optimization for Reinforcement Learning.
Proceedings of the 3rd Annual Conference on Robot Learning, 2019

Orthogonal Estimation of Wasserstein Distances.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

KAMA-NNs: Low-dimensional Rotation Based Neural Networks.
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018
Excluding pairs of tournaments.
J. Graph Theory, 2018

On the Needs for Rotations in Hypercubic Quantization Hashing.
CoRR, 2018

Excluding Hooks and their Complements.
Electron. J. Comb., 2018

Learning-based Air Data System for Safe and Efficient Control of Fixed-wing Aerial Vehicles.
Proceedings of the 2018 IEEE International Symposium on Safety, 2018

Graph sketching-based Space-efficient Data Clustering.
Proceedings of the 2018 SIAM International Conference on Data Mining, 2018

Adaptive anonymization of data using b-edge cover.
Proceedings of the International Conference for High Performance Computing, 2018

Geometrically Coupled Monte Carlo Sampling.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Optimizing Simulations with Noise-Tolerant Structured Exploration.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

VisualBackProp: Efficient Visualization of CNNs for Autonomous Driving.
Proceedings of the 2018 IEEE International Conference on Robotics and Automation, 2018

Structured Evolution with Compact Architectures for Scalable Policy Optimization.
Proceedings of the 35th International Conference on Machine Learning, 2018

Initialization matters: Orthogonal Predictive State Recurrent Neural Networks.
Proceedings of the 6th International Conference on Learning Representations, 2018

The Geometry of Random Features.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2017
Manifold Regularization for Kernelized LSTD.
CoRR, 2017

Graph sketching-based Massive Data Clustering.
CoRR, 2017

Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car.
CoRR, 2017

On Blackbox Backpropagation and Jacobian Sensing.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Structured adaptive and random spinners for fast machine learning computations.
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016
Differentially-private learning of low dimensional manifolds.
Theor. Comput. Sci., 2016

TripleSpin - a generic compact paradigm for fast machine learning computations.
CoRR, 2016

Fast nonlinear embeddings via structured matrices.
CoRR, 2016

On the boosting ability of top-down decision tree learning algorithm for multiclass classification.
CoRR, 2016

VisualBackProp: visualizing CNNs for autonomous driving.
CoRR, 2016

Orthogonal Random Features.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Recycling Randomness with Structure for Sublinear time Kernel Expansions.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Binary embeddings with structured hashed projections.
Proceedings of the 33nd International Conference on Machine Learning, 2016

Quantization based Fast Inner Product Search.
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

2015
EH-suprema of tournaments with no nontrivial homogeneous sets.
J. Comb. Theory, Ser. B, 2015

Forcing large transitive subtournaments.
J. Comb. Theory, Ser. B, 2015

An $\tilde{O}(\frac{1}{\sqrt{T}})$-error online algorithm for retrieving heavily perturbated statistical databases in the low-dimensional querying mode.
CoRR, 2015

Fast Online Clustering with Randomized Skeleton Sets.
CoRR, 2015

Coloring tournaments with forbidden substructures.
CoRR, 2015

Efficient data hashing with structured binary embeddings.
CoRR, 2015

Learning how to rank from heavily perturbed statistics - digraph clustering approach.
CoRR, 2015

An Optimal Online Algorithm For Retrieving Heavily Perturbed Statistical Databases In The Low-Dimensional Querying Model.
Proceedings of the 24th ACM International Conference on Information and Knowledge Management, 2015

2014
Tournaments with near-linear transitive subsets.
J. Comb. Theory, Ser. B, 2014

Differentially- and non-differentially-private random decision trees.
CoRR, 2014

Notes on using Determinantal Point Processes for Clustering with Applications to Text Clustering.
CoRR, 2014

2013
Upper Bounds for Erdös-Hajnal Coefficients of Tournaments.
J. Graph Theory, 2013

Tournaments and colouring.
J. Comb. Theory, Ser. B, 2013

Adaptive Anonymity via <i>b</i>-Matching.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

2012
The power of the dinur-nissim algorithm: breaking privacy of statistical and graph databases.
Proceedings of the 31st ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems, 2012


  Loading...