Search Results for author: Akshat Kumar

Found 13 papers, 4 papers with code

DeepTIMe: Deep Time-Index Meta-Learning for Non-Stationary Time-Series Forecasting

1 code implementation13 Jul 2022 Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi

Yet, despite the attractive properties of time-index based models, such as being a continuous signal function over time leading to smooth representations, little attention has been given to them.

Meta-Learning Time Series Forecasting

Sample-efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs

no code implementations23 Mar 2022 Siow Meng Low, Akshat Kumar, Scott Sanner

This novel formulation of DRP learning as iterative lower bound optimization (ILBO) is particularly appealing because (i) each step is structurally easier to optimize than the overall objective, (ii) it guarantees a monotonically improving objective under certain theoretical conditions, and (iii) it reuses samples between iterations thus lowering sample complexity.

InfraredTags: Embedding Invisible AR Markers and Barcodes Using Low-Cost, Infrared-Based 3D Printing and Imaging Tools

no code implementations12 Feb 2022 Mustafa Doga Dogan, Ahmad Taka, Michael Lu, Yunyi Zhu, Akshat Kumar, Aakar Gupta, Stefanie Mueller

We present InfraredTags, which are 2D markers and barcodes imperceptible to the naked eye that can be 3D printed as part of objects, and detected rapidly by low-cost near-infrared cameras.

Object Tracking

CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting

1 code implementation ICLR 2022 Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi

Motivated by the recent success of representation learning in computer vision and natural language processing, we argue that a more promising paradigm for time series forecasting, is to first learn disentangled feature representations, followed by a simple regression fine-tuning step -- we justify such a paradigm from a causal perspective.

Contrastive Learning Representation Learning +1

Manifold learning via quantum dynamics

no code implementations20 Dec 2021 Akshat Kumar, Mohan Sarovar

We introduce an algorithm for computing geodesics on sampled manifolds that relies on simulation of quantum dynamics on a graph embedding of the sampled data.

Dimensionality Reduction Graph Embedding +1

Combining Propositional Logic Based Decision Diagrams with Decision Making in Urban Systems

no code implementations9 Nov 2020 Jiajing Ling, Kushagra Chandak, Akshat Kumar

Solving multiagent problems can be an uphill task due to uncertainty in the environment, partial observability, and scalability of the problem at hand.

Decision Making reinforcement-learning

Resource Constrained Deep Reinforcement Learning

no code implementations3 Dec 2018 Abhinav Bhatia, Pradeep Varakantham, Akshat Kumar

However, existing Deep RL methods are unable to handle combinatorial action spaces and constraints on allocation of resources.

Management reinforcement-learning

Credit Assignment For Collective Multiagent RL With Global Rewards

no code implementations NeurIPS 2018 Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau

Scaling decision theoretic planning to large multiagent systems is challenging due to uncertainty and partial observability in the environment.

Robust Optimization for Tree-Structured Stochastic Network Design

no code implementations1 Dec 2016 Xiaojian Wu, Akshat Kumar, Daniel Sheldon, Shlomo Zilberstein

We therefore address the robust river network design problem where the goal is to optimize river connectivity for fish movement by removing barriers.

MAP Estimation for Graphical Models by Likelihood Maximization

no code implementations NeurIPS 2010 Akshat Kumar, Shlomo Zilberstein

We experiment on the real-world protein design dataset and show that EM's convergence rate is significantly higher than the previous LP relaxation based approach MPLP.

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