Search Results for author: Karan Singh

Found 24 papers, 4 papers with code

A Boosting Approach to Reinforcement Learning

no code implementations22 Aug 2021 Nataly Brukhim, Elad Hazan, Karan Singh

We study efficient algorithms for reinforcement learning in Markov decision processes whose complexity is independent of the number of states.

SurgeonAssist-Net: Towards Context-Aware Head-Mounted Display-Based Augmented Reality for Surgical Guidance

1 code implementation13 Jul 2021 Mitchell Doughty, Karan Singh, Nilesh R. Ghugre

On a widely used benchmark dataset for laparoscopic surgical workflow, our implementation competes with state-of-the-art approaches in prediction accuracy for automated task recognition, and yet requires 7. 4x fewer parameters, 10. 2x fewer floating point operations per second (FLOPS), is 7. 0x faster for inference on a CPU, and is capable of near real-time performance on the Microsoft HoloLens 2 OST-HMD.

A Regret Minimization Approach to Iterative Learning Control

no code implementations26 Feb 2021 Naman Agarwal, Elad Hazan, Anirudha Majumdar, Karan Singh

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics.

Deluca -- A Differentiable Control Library: Environments, Methods, and Benchmarking

1 code implementation19 Feb 2021 Paula Gradu, John Hallman, Daniel Suo, Alex Yu, Naman Agarwal, Udaya Ghai, Karan Singh, Cyril Zhang, Anirudha Majumdar, Elad Hazan

We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite.

OpenAI Gym

Boosting for Online Convex Optimization

no code implementations18 Feb 2021 Elad Hazan, Karan Singh

In this access model, we give an efficient boosting algorithm that guarantees near-optimal regret against the convex hull of the base class.

Decision Making

Machine Learning for Mechanical Ventilation Control

no code implementations12 Feb 2021 Daniel Suo, Cyril Zhang, Paula Gradu, Udaya Ghai, Xinyi Chen, Edgar Minasyan, Naman Agarwal, Karan Singh, Julienne LaChance, Tom Zajdel, Manuel Schottdorf, Daniel Cohen, Elad Hazan

We consider the problem of controlling an invasive mechanical ventilator for pressure-controlled ventilation: a controller must let air in and out of a sedated patient's lungs according to a trajectory of airway pressures specified by a clinician.

Coexistance of non-Fermi liquid behavior and bi-quadratic exchange coupling in La-substituted CeGe: Non-linear susceptibility and DFT + DMFT study

no code implementations17 Dec 2020 Karan Singh, Antik Sihi, Sudhir K. Pandey, K. Mukherjee

Under the application of magnetic fields, local moments interact spatially through conduction electrons resulting in magnetic fluctuations.

Strongly Correlated Electrons

RigNet: Neural Rigging for Articulated Characters

1 code implementation1 May 2020 Zhan Xu, Yang Zhou, Evangelos Kalogerakis, Chris Landreth, Karan Singh

We present RigNet, an end-to-end automated method for producing animation rigs from input character models.

No-Regret Prediction in Marginally Stable Systems

no code implementations6 Feb 2020 Udaya Ghai, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang

This requires a refined regret analysis, including a structural lemma showing the current state of the system to be a small linear combination of past states, even if the state grows polynomially.

Improper Learning for Non-Stochastic Control

no code implementations25 Jan 2020 Max Simchowitz, Karan Singh, Elad Hazan

We consider the problem of controlling a possibly unknown linear dynamical system with adversarial perturbations, adversarially chosen convex loss functions, and partially observed states, known as non-stochastic control.

The Nonstochastic Control Problem

no code implementations27 Nov 2019 Elad Hazan, Sham M. Kakade, Karan Singh

We consider the problem of controlling an unknown linear dynamical system in the presence of (nonstochastic) adversarial perturbations and adversarial convex loss functions.

Logarithmic Regret for Online Control

no code implementations NeurIPS 2019 Naman Agarwal, Elad Hazan, Karan Singh

We study optimal regret bounds for control in linear dynamical systems under adversarially changing strongly convex cost functions, given the knowledge of transition dynamics.

Predicting Animation Skeletons for 3D Articulated Models via Volumetric Nets

no code implementations22 Aug 2019 Zhan Xu, Yang Zhou, Evangelos Kalogerakis, Karan Singh

We present a learning method for predicting animation skeletons for input 3D models of articulated characters.

Online Control with Adversarial Disturbances

no code implementations23 Feb 2019 Naman Agarwal, Brian Bullins, Elad Hazan, Sham M. Kakade, Karan Singh

We study the control of a linear dynamical system with adversarial disturbances (as opposed to statistical noise).

Provably Efficient Maximum Entropy Exploration

2 code implementations6 Dec 2018 Elad Hazan, Sham M. Kakade, Karan Singh, Abby Van Soest

Suppose an agent is in a (possibly unknown) Markov Decision Process in the absence of a reward signal, what might we hope that an agent can efficiently learn to do?

Efficient Full-Matrix Adaptive Regularization

no code implementations ICLR 2019 Naman Agarwal, Brian Bullins, Xinyi Chen, Elad Hazan, Karan Singh, Cyril Zhang, Yi Zhang

Due to the large number of parameters of machine learning problems, full-matrix preconditioning methods are prohibitively expensive.

Color Sails: Discrete-Continuous Palettes for Deep Color Exploration

no code implementations7 Jun 2018 Maria Shugrina, Amlan Kar, Karan Singh, Sanja Fidler

Then, the user can adjust color sail parameters to change the base colors, their blending behavior and the number of colors, exploring a wide range of options for the original design.

VisemeNet: Audio-Driven Animator-Centric Speech Animation

no code implementations24 May 2018 Yang Zhou, Zhan Xu, Chris Landreth, Evangelos Kalogerakis, Subhransu Maji, Karan Singh

We present a novel deep-learning based approach to producing animator-centric speech motion curves that drive a JALI or standard FACS-based production face-rig, directly from input audio.

Graphics

Spectral Filtering for General Linear Dynamical Systems

no code implementations NeurIPS 2018 Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang

We give a polynomial-time algorithm for learning latent-state linear dynamical systems without system identification, and without assumptions on the spectral radius of the system's transition matrix.

Towards Provable Control for Unknown Linear Dynamical Systems

no code implementations ICLR 2018 Sanjeev Arora, Elad Hazan, Holden Lee, Karan Singh, Cyril Zhang, Yi Zhang

We study the control of symmetric linear dynamical systems with unknown dynamics and a hidden state.

Learning Linear Dynamical Systems via Spectral Filtering

no code implementations NeurIPS 2017 Elad Hazan, Karan Singh, Cyril Zhang

We present an efficient and practical algorithm for the online prediction of discrete-time linear dynamical systems with a symmetric transition matrix.

Time Series

Efficient Regret Minimization in Non-Convex Games

no code implementations ICML 2017 Elad Hazan, Karan Singh, Cyril Zhang

We consider regret minimization in repeated games with non-convex loss functions.

Dynamic Task Allocation for Crowdsourcing Settings

no code implementations30 Jan 2017 Angela Zhou, Irineo Cabreros, Karan Singh

We consider the problem of optimal budget allocation for crowdsourcing problems, allocating users to tasks to maximize our final confidence in the crowdsourced answers.

The Price of Differential Privacy For Online Learning

no code implementations ICML 2017 Naman Agarwal, Karan Singh

We design differentially private algorithms for the problem of online linear optimization in the full information and bandit settings with optimal $\tilde{O}(\sqrt{T})$ regret bounds.

Multi-Armed Bandits

Cannot find the paper you are looking for? You can Submit a new open access paper.