Search Results for author: Janardhan Rao Doppa

Found 26 papers, 13 papers with code

Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization

1 code implementation13 Oct 2021 Syrine Belakaria, Aryan Deshwal, Janardhan Rao Doppa

We consider the problem of black-box multi-objective optimization (MOO) using expensive function evaluations (also referred to as experiments), where the goal is to approximate the true Pareto set of solutions by minimizing the total resource cost of experiments.

CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning

1 code implementation30 Sep 2021 Garrett Wilson, Janardhan Rao Doppa, Diane J. Cook

CALDA synergistically combines the principles of contrastive learning and adversarial learning to robustly support multi-source UDA (MS-UDA) for time series data.

Activity Recognition Contrastive Learning +3

Bayesian Optimization over Hybrid Spaces

1 code implementation8 Jun 2021 Aryan Deshwal, Syrine Belakaria, Janardhan Rao Doppa

We develop a principled approach for constructing diffusion kernels over hybrid spaces by utilizing the additive kernel formulation, which allows additive interactions of all orders in a tractable manner.

SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms

no code implementations23 Mar 2021 Nitthilan Kannappan Jayakodi, Janardhan Rao Doppa, Partha Pratim Pande

The key idea behind SETGAN for an image generation task is for a given input image, we train a GAN on a remote server and use the trained model on edge devices.

Image Generation SSIM +1

Optimizing Discrete Spaces via Expensive Evaluations: A Learning to Search Framework

no code implementations14 Dec 2020 Aryan Deshwal, Syrine Belakaria, Janardhan Rao Doppa, Alan Fern

We consider the problem of optimizing expensive black-box functions over discrete spaces (e. g., sets, sequences, graphs).

Mercer Features for Efficient Combinatorial Bayesian Optimization

1 code implementation14 Dec 2020 Aryan Deshwal, Syrine Belakaria, Janardhan Rao Doppa

In this paper, we propose an efficient approach referred as Mercer Features for Combinatorial Bayesian Optimization (MerCBO).

Multi-Fidelity Multi-Objective Bayesian Optimization: An Output Space Entropy Search Approach

no code implementations2 Nov 2020 Syrine Belakaria, Aryan Deshwal, Janardhan Rao Doppa

The overall goal is to approximate the true Pareto set of solutions by minimizing the resources consumed for function evaluations.

Information-Theoretic Multi-Objective Bayesian Optimization with Continuous Approximations

no code implementations12 Sep 2020 Syrine Belakaria, Aryan Deshwal, Janardhan Rao Doppa

The key idea is to select the sequence of input and function approximations for multiple objectives which maximize the information gain per unit cost for the optimal Pareto front.

Max-value Entropy Search for Multi-Objective Bayesian Optimization with Constraints

1 code implementation1 Sep 2020 Syrine Belakaria, Aryan Deshwal, Janardhan Rao Doppa

We consider the problem of constrained multi-objective blackbox optimization using expensive function evaluations, where the goal is to approximate the true Pareto set of solutions satisfying a set of constraints while minimizing the number of function evaluations.

Online Adaptive Learning for Runtime Resource Management of Heterogeneous SoCs

no code implementations22 Aug 2020 Sumit K. Mandal, Umit Y. Ogras, Janardhan Rao Doppa, Raid Z. Ayoub, Michael Kishinevsky, Partha P. Pande

Dynamic resource management has become one of the major areas of research in modern computer and communication system design due to lower power consumption and higher performance demands.

Imitation Learning

Scalable Combinatorial Bayesian Optimization with Tractable Statistical models

1 code implementation18 Aug 2020 Aryan Deshwal, Syrine Belakaria, Janardhan Rao Doppa

Based on recent advances in submodular relaxation (Ito and Fujimaki, 2016) for solving Binary Quadratic Programs, we study an approach referred as Parametrized Submodular Relaxation (PSR) towards the goal of improving the scalability and accuracy of solving AFO problems for BOCS model.

Uncertainty aware Search Framework for Multi-Objective Bayesian Optimization with Constraints

1 code implementation16 Aug 2020 Syrine Belakaria, Aryan Deshwal, Janardhan Rao Doppa

We consider the problem of constrained multi-objective (MO) blackbox optimization using expensive function evaluations, where the goal is to approximate the true Pareto set of solutions satisfying a set of constraints while minimizing the number of function evaluations.

Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data

2 code implementations22 May 2020 Garrett Wilson, Janardhan Rao Doppa, Diane J. Cook

First, we propose a novel Convolutional deep Domain Adaptation model for Time Series data (CoDATS) that significantly improves accuracy and training time over state-of-the-art DA strategies on real-world sensor data benchmarks.

Domain Adaptation Time Series

An Energy-Aware Online Learning Framework for Resource Management in Heterogeneous Platforms

no code implementations20 Mar 2020 Sumit K. Mandal, Ganapati Bhat, Janardhan Rao Doppa, Partha Pratim Pande, Umit Y. Ogras

To address this need, system-on-chips (SoC) that are at the heart of these devices provide a variety of control knobs, such as the number of active cores and their voltage/frequency levels.

Imitation Learning

One-Shot Induction of Generalized Logical Concepts via Human Guidance

no code implementations15 Dec 2019 Mayukh Das, Nandini Ramanan, Janardhan Rao Doppa, Sriraam Natarajan

First, we define a distance measure between candidate concept representations that improves the efficiency of search for target concept and generalization.

Inductive logic programming

Max-value Entropy Search for Multi-Objective Bayesian Optimization

1 code implementation NeurIPS 2019 Syrine Belakaria, Aryan Deshwal, Janardhan Rao Doppa

We consider the problem of multi-objective (MO) blackbox optimization using expensive function evaluations, where the goal is to approximate the true Pareto-set of solutions by minimizing the number of function evaluations.

Bayesian Optimisation Global Optimization +1

Active Anomaly Detection via Ensembles: Insights, Algorithms, and Interpretability

2 code implementations23 Jan 2019 Shubhomoy Das, Md. Rakibul Islam, Nitthilan Kannappan Jayakodi, Janardhan Rao Doppa

In this paper, we study the problem of active learning to automatically tune ensemble of anomaly detectors to maximize the number of true anomalies discovered.

Active Learning Anomaly Detection

Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems

1 code implementation20 Oct 2018 Biresh Kumar Joardar, Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu

Our results show that these generalized 3D NoCs only incur a 1. 8% (36-tile system) and 1. 1% (64-tile system) average performance loss compared to application-specific NoCs.

GLAD: GLocalized Anomaly Detection via Human-in-the-Loop Learning

2 code implementations2 Oct 2018 Md. Rakibul Islam, Shubhomoy Das, Janardhan Rao Doppa, Sriraam Natarajan

Human analysts that use anomaly detection systems in practice want to retain the use of simple and explainable global anomaly detectors.

Anomaly Detection

Active Anomaly Detection via Ensembles

2 code implementations17 Sep 2018 Shubhomoy Das, Md. Rakibul Islam, Nitthilan Kannappan Jayakodi, Janardhan Rao Doppa

First, we present an important insight into how anomaly detector ensembles are naturally suited for active learning.

Active Learning Anomaly Detection

Learning Scripts as Hidden Markov Models

no code implementations11 Sep 2018 J. Walker Orr, Prasad Tadepalli, Janardhan Rao Doppa, Xiaoli Fern, Thomas G. Dietterich

Scripts have been proposed to model the stereotypical event sequences found in narratives.

Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis

no code implementations30 Nov 2017 Ryan Gary Kim, Janardhan Rao Doppa, Partha Pratim Pande, Diana Marculescu, Radu Marculescu

Tight collaboration between experts of machine learning and manycore system design is necessary to create a data-driven manycore design framework that integrates both learning and expert knowledge.

HC-Search for Structured Prediction in Computer Vision

no code implementations CVPR 2015 Michael Lam, Janardhan Rao Doppa, Sinisa Todorovic, Thomas G. Dietterich

The mainstream approach to structured prediction problems in computer vision is to learn an energy function such that the solution minimizes that function.

Monocular Depth Estimation Object Detection +2

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