Search Results for author: Vikas Sindhwani

Found 44 papers, 4 papers with code

Safely Learning Dynamical Systems

no code implementations20 May 2023 Amir Ali Ahmadi, Abraar Chaudhry, Vikas Sindhwani, Stephen Tu

For $T=2$, we give a semidefinite representation of the set of safe initial conditions and show that $\lceil n/2 \rceil$ trajectories generically suffice for safe learning.

Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization

no code implementations19 Oct 2022 Thomas Lew, Sumeet Singh, Mario Prats, Jeffrey Bingham, Jonathan Weisz, Benjie Holson, Xiaohan Zhang, Vikas Sindhwani, Yao Lu, Fei Xia, Peng Xu, Tingnan Zhang, Jie Tan, Montserrat Gonzalez

This problem is challenging, as it requires planning wiping actions while reasoning over uncertain latent dynamics of crumbs and spills captured via high-dimensional visual observations.

reinforcement-learning Reinforcement Learning (RL)

Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation

no code implementations22 Sep 2022 Xuesu Xiao, Tingnan Zhang, Krzysztof Choromanski, Edward Lee, Anthony Francis, Jake Varley, Stephen Tu, Sumeet Singh, Peng Xu, Fei Xia, Sven Mikael Persson, Dmitry Kalashnikov, Leila Takayama, Roy Frostig, Jie Tan, Carolina Parada, Vikas Sindhwani

Despite decades of research, existing navigation systems still face real-world challenges when deployed in the wild, e. g., in cluttered home environments or in human-occupied public spaces.

Imitation Learning

Implicit Two-Tower Policies

no code implementations2 Aug 2022 Yunfan Zhao, Qingkai Pan, Krzysztof Choromanski, Deepali Jain, Vikas Sindhwani

We present a new class of structured reinforcement learning policy-architectures, Implicit Two-Tower (ITT) policies, where the actions are chosen based on the attention scores of their learnable latent representations with those of the input states.

OpenAI Gym Vocal Bursts Valence Prediction

Multiscale Sensor Fusion and Continuous Control with Neural CDEs

no code implementations16 Mar 2022 Sumeet Singh, Francis McCann Ramirez, Jacob Varley, Andy Zeng, Vikas Sindhwani

Though robot learning is often formulated in terms of discrete-time Markov decision processes (MDPs), physical robots require near-continuous multiscale feedback control.

Continuous Control Sensor Fusion

Hybrid Random Features

1 code implementation ICLR 2022 Krzysztof Choromanski, Haoxian Chen, Han Lin, Yuanzhe Ma, Arijit Sehanobish, Deepali Jain, Michael S Ryoo, Jake Varley, Andy Zeng, Valerii Likhosherstov, Dmitry Kalashnikov, Vikas Sindhwani, Adrian Weller

We propose a new class of random feature methods for linearizing softmax and Gaussian kernels called hybrid random features (HRFs) that automatically adapt the quality of kernel estimation to provide most accurate approximation in the defined regions of interest.


Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks

no code implementations6 Dec 2020 Daniel Seita, Pete Florence, Jonathan Tompson, Erwin Coumans, Vikas Sindhwani, Ken Goldberg, Andy Zeng

Goals cannot be as easily specified as rigid object poses, and may involve complex relative spatial relations such as "place the item inside the bag".

Ode to an ODE

no code implementations NeurIPS 2020 Krzysztof M. Choromanski, Jared Quincy Davis, Valerii Likhosherstov, Xingyou Song, Jean-Jacques Slotine, Jacob Varley, Honglak Lee, Adrian Weller, Vikas Sindhwani

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).

Safely Learning Dynamical Systems from Short Trajectories

no code implementations24 Nov 2020 Amir Ali Ahmadi, Abraar Chaudhry, Vikas Sindhwani, Stephen Tu

For our first two results, we consider the setting of safely learning linear dynamics.

Learning Stability Certificates from Data

no code implementations13 Aug 2020 Nicholas M. Boffi, Stephen Tu, Nikolai Matni, Jean-Jacques E. Slotine, Vikas Sindhwani

Many existing tools in nonlinear control theory for establishing stability or safety of a dynamical system can be distilled to the construction of a certificate function that guarantees a desired property.

An Ode to an ODE

no code implementations NeurIPS 2020 Krzysztof Choromanski, Jared Quincy Davis, Valerii Likhosherstov, Xingyou Song, Jean-Jacques Slotine, Jacob Varley, Honglak Lee, Adrian Weller, Vikas Sindhwani

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).

Time Dependence in Non-Autonomous Neural ODEs

no code implementations ICLR Workshop DeepDiffEq 2019 Jared Quincy Davis, Krzysztof Choromanski, Jake Varley, Honglak Lee, Jean-Jacques Slotine, Valerii Likhosterov, Adrian Weller, Ameesh Makadia, Vikas Sindhwani

Neural Ordinary Differential Equations (ODEs) are elegant reinterpretations of deep networks where continuous time can replace the discrete notion of depth, ODE solvers perform forward propagation, and the adjoint method enables efficient, constant memory backpropagation.

Image Classification Video Prediction

Robotic Table Tennis with Model-Free Reinforcement Learning

no code implementations31 Mar 2020 Wenbo Gao, Laura Graesser, Krzysztof Choromanski, Xingyou Song, Nevena Lazic, Pannag Sanketi, Vikas Sindhwani, Navdeep Jaitly

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.

reinforcement-learning Reinforcement Learning (RL)

Stochastic Flows and Geometric Optimization on the Orthogonal Group

no code implementations ICML 2020 Krzysztof Choromanski, David Cheikhi, Jared Davis, Valerii Likhosherstov, Achille Nazaret, Achraf Bahamou, Xingyou Song, Mrugank Akarte, Jack Parker-Holder, Jacob Bergquist, Yuan Gao, Aldo Pacchiano, Tamas Sarlos, Adrian Weller, Vikas Sindhwani

We present a new class of stochastic, geometrically-driven optimization algorithms on the orthogonal group $O(d)$ and naturally reductive homogeneous manifolds obtained from the action of the rotation group $SO(d)$.

Metric Learning Stochastic Optimization

Policies Modulating Trajectory Generators

3 code implementations7 Oct 2019 Atil Iscen, Ken Caluwaerts, Jie Tan, Tingnan Zhang, Erwin Coumans, Vikas Sindhwani, Vincent Vanhoucke

We propose an architecture for learning complex controllable behaviors by having simple Policies Modulate Trajectory Generators (PMTG), a powerful combination that can provide both memory and prior knowledge to the controller.

Learning Stabilizable Nonlinear Dynamics with Contraction-Based Regularization

1 code implementation29 Jul 2019 Sumeet Singh, Spencer M. Richards, Vikas Sindhwani, Jean-Jacques E. Slotine, Marco Pavone

We propose a novel framework for learning stabilizable nonlinear dynamical systems for continuous control tasks in robotics.

Continuous Control

Data Efficient Reinforcement Learning for Legged Robots

no code implementations8 Jul 2019 Yuxiang Yang, Ken Caluwaerts, Atil Iscen, Tingnan Zhang, Jie Tan, Vikas Sindhwani

We present a model-based framework for robot locomotion that achieves walking based on only 4. 5 minutes (45, 000 control steps) of data collected on a quadruped robot.

reinforcement-learning Reinforcement Learning (RL) +1

Provably Robust Blackbox Optimization for Reinforcement Learning

no code implementations7 Mar 2019 Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Deepali Jain, Yuxiang Yang, Atil Iscen, Jasmine Hsu, Vikas Sindhwani

Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization problems in Robotics.

reinforcement-learning Reinforcement Learning (RL) +1

Learning Contracting Vector Fields For Stable Imitation Learning

no code implementations13 Apr 2018 Vikas Sindhwani, Stephen Tu, Mohi Khansari

We propose a new non-parametric framework for learning incrementally stable dynamical systems x' = f(x) from a set of sampled trajectories.

Imitation Learning

Structured Evolution with Compact Architectures for Scalable Policy Optimization

no code implementations ICML 2018 Krzysztof Choromanski, Mark Rowland, Vikas Sindhwani, Richard E. Turner, Adrian Weller

We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines and with provable theoretical guarantees.

OpenAI Gym Text-to-Image Generation

On Blackbox Backpropagation and Jacobian Sensing

no code implementations NeurIPS 2017 Krzysztof M. Choromanski, Vikas Sindhwani

From a small number of calls to a given “blackbox" on random input perturbations, we show how to efficiently recover its unknown Jacobian, or estimate the left action of its Jacobian on a given vector.

Manifold Regularization for Kernelized LSTD

no code implementations15 Oct 2017 Xinyan Yan, Krzysztof Choromanski, Byron Boots, Vikas Sindhwani

Policy evaluation or value function or Q-function approximation is a key procedure in reinforcement learning (RL).

Policy Gradient Methods Reinforcement Learning (RL)

Geometry of 3D Environments and Sum of Squares Polynomials

no code implementations22 Nov 2016 Amir Ali Ahmadi, Georgina Hall, Ameesh Makadia, Vikas Sindhwani

Motivated by applications in robotics and computer vision, we study problems related to spatial reasoning of a 3D environment using sublevel sets of polynomials.

Hierarchically Compositional Kernels for Scalable Nonparametric Learning

no code implementations2 Aug 2016 Jie Chen, Haim Avron, Vikas Sindhwani

We propose a novel class of kernels to alleviate the high computational cost of large-scale nonparametric learning with kernel methods.

Recycling Randomness with Structure for Sublinear time Kernel Expansions

no code implementations29 May 2016 Krzysztof Choromanski, Vikas Sindhwani

We propose a scheme for recycling Gaussian random vectors into structured matrices to approximate various kernel functions in sublinear time via random embeddings.

Learning Compact Recurrent Neural Networks

no code implementations9 Apr 2016 Zhiyun Lu, Vikas Sindhwani, Tara N. Sainath

Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks.

speech-recognition Speech Recognition

Structured Transforms for Small-Footprint Deep Learning

no code implementations NeurIPS 2015 Vikas Sindhwani, Tara N. Sainath, Sanjiv Kumar

We consider the task of building compact deep learning pipelines suitable for deployment on storage and power constrained mobile devices.

Keyword Spotting speech-recognition +1

Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels

no code implementations29 Dec 2014 Haim Avron, Vikas Sindhwani, Jiyan Yang, Michael Mahoney

These approximate feature maps arise as Monte Carlo approximations to integral representations of shift-invariant kernel functions (e. g., Gaussian kernel).

Learning Machines Implemented on Non-Deterministic Hardware

no code implementations9 Sep 2014 Suyog Gupta, Vikas Sindhwani, Kailash Gopalakrishnan

This paper highlights new opportunities for designing large-scale machine learning systems as a consequence of blurring traditional boundaries that have allowed algorithm designers and application-level practitioners to stay -- for the most part -- oblivious to the details of the underlying hardware-level implementations.

BIG-bench Machine Learning

Random Laplace Feature Maps for Semigroup Kernels on Histograms

no code implementations CVPR 2014 Jiyan Yang, Vikas Sindhwani, Quanfu Fan, Haim Avron, Michael W. Mahoney

With the goal of accelerating the training and testing complexity of nonlinear kernel methods, several recent papers have proposed explicit embeddings of the input data into low-dimensional feature spaces, where fast linear methods can instead be used to generate approximate solutions.

Event Detection Image Classification

Near-separable Non-negative Matrix Factorization with $\ell_1$- and Bregman Loss Functions

no code implementations27 Dec 2013 Abhishek Kumar, Vikas Sindhwani

Recently, a family of tractable NMF algorithms have been proposed under the assumption that the data matrix satisfies a separability condition Donoho & Stodden (2003); Arora et al. (2012).

Sketching Structured Matrices for Faster Nonlinear Regression

no code implementations NeurIPS 2013 Haim Avron, Vikas Sindhwani, David Woodruff

Motivated by the desire to extend fast randomized techniques to nonlinear $l_p$ regression, we consider a class of structured regression problems.


Non-parametric Group Orthogonal Matching Pursuit for Sparse Learning with Multiple Kernels

no code implementations NeurIPS 2011 Vikas Sindhwani, Aurelie C. Lozano

We consider regularized risk minimization in a large dictionary of Reproducing kernel Hilbert Spaces (RKHSs) over which the target function has a sparse representation.

Generalization Bounds Sparse Learning

Regularized Co-Clustering with Dual Supervision

no code implementations NeurIPS 2008 Vikas Sindhwani, Jianying Hu, Aleksandra Mojsilovic

By attempting to simultaneously partition both the rows (examples) and columns (features) of a data matrix, Co-clustering algorithms often demonstrate surpris- ingly impressive performance improvements over traditional one-sided (row) clustering techniques.

Clustering graph partitioning +1

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