Search Results for author:
Found 51 papers, 28 papers with code
Atleus: Accelerating Transformers on the Edge Enabled by 3D Heterogeneous Manycore Architectures
Experimental results demonstrate that Atleus outperforms existing state-of-the-art by up to 56x and 64. 5x in terms of performance and energy efficiency respectively
Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning
Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints.
Non-Myopic Multi-Objective Bayesian Optimization
We address this challenge by using hypervolume improvement (HVI) as our scalarization approach, which allows us to use a lower-bound on the Bellman equation to approximate the finite-horizon using a batch expected hypervolume improvement (EHVI) acquisition function (AF) for MOO.
HeTraX: Energy Efficient 3D Heterogeneous Manycore Architecture for Transformer Acceleration
Transformers have revolutionized deep learning and generative modeling to enable unprecedented advancements in natural language processing tasks and beyond.
Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes
We consider the problem of active learning for global sensitivity analysis of expensive black-box functions.
Pareto Front-Diverse Batch Multi-Objective Bayesian Optimization
We solve a cheap MOO problem by assigning the selected acquisition function for each expensive objective function to obtain a candidate set of inputs for evaluation.
Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration
In contrast to the standard class-conditional CP (CCP) method that uniformly thresholds the class-wise conformity score for each class, the augmented label rank calibration step allows RC3P to selectively iterate this class-wise thresholding subroutine only for a subset of classes whose class-wise top-k error is small.
Streamflow Prediction with Uncertainty Quantification for Water Management: A Constrained Reasoning and Learning Approach
Predicting the spatiotemporal variation in streamflow along with uncertainty quantification enables decision-making for sustainable management of scarce water resources.
Offline Model-Based Optimization via Policy-Guided Gradient Search
Offline optimization is an emerging problem in many experimental engineering domains including protein, drug or aircraft design, where online experimentation to collect evaluation data is too expensive or dangerous.
Dataflow-Aware PIM-Enabled Manycore Architecture for Deep Learning Workloads
However, as the complexity of Deep convolutional neural networks (DNNs) grows, we need to design a manycore architecture with multiple ReRAM-based processing elements (PEs) on a single chip.
FARe: Fault-Aware GNN Training on ReRAM-based PIM Accelerators
Experimental results demonstrate that FARe framework can restore GNN test accuracy by 47. 6% on faulty ReRAM hardware with a ~1% timing overhead compared to the fault-free counterpart.
Preference-Aware Constrained Multi-Objective Bayesian Optimization
Our overall goal is to approximate the optimal Pareto set over the small fraction of feasible input designs.
Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis
Safe deployment of deep neural networks in high-stake real-world applications requires theoretically sound uncertainty quantification.
Bayesian Optimization over High-Dimensional Combinatorial Spaces via Dictionary-based Embeddings
We use Bayesian Optimization (BO) and propose a novel surrogate modeling approach for efficiently handling a large number of binary and categorical parameters.
Human-guided Collaborative Problem Solving: A Natural Language based Framework
We consider the problem of human-machine collaborative problem solving as a planning task coupled with natural language communication.
Domain Adaptation Under Behavioral and Temporal Shifts for Natural Time Series Mobile Activity Recognition
Because of the large variations present in human behavior, we collect data from many participants across two different age groups.
Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
Despite the success of deep neural networks (DNNs) for real-world applications over time-series data such as mobile health, little is known about how to train robust DNNs for time-series domain due to its unique characteristics compared to images and text data.
Out-of-Distribution Detection in Time-Series Domain: A Novel Seasonal Ratio Scoring Approach
Experiments on diverse real-world benchmarks demonstrate that the SRS method is well-suited for time-series OOD detection when compared to baseline methods.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+2
Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features
We also provide certified bounds on the norm of the statistical features for constructing adversarial examples.
Dynamic Time Warping based Adversarial Framework for Time-Series Domain
Despite the rapid progress on research in adversarial robustness of deep neural networks (DNNs), there is little principled work for the time-series domain.
Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach
The rising growth of deep neural networks (DNNs) and datasets in size motivates the need for efficient solutions for simultaneous model selection and training.
Uncertainty-Aware Search Framework for Multi-Objective Bayesian Optimization
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 while minimizing the number of function evaluations.
Adaptive Energy Management for Self-Sustainable Wearables in Mobile Health
To solve this problem, we propose a principled algorithm referred as AdaEM.
Bayesian Optimization over Permutation Spaces
First, BOPS-T employs Gaussian process (GP) surrogate model with Kendall kernels and a Tractable acquisition function optimization approach based on Thompson sampling to select the sequence of permutations for evaluation.
Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces
The key idea is to define a novel structure-coupled kernel that explicitly integrates the structural information from decoded structures with the learned latent space representation for better surrogate modeling.
Output Space Entropy Search Framework for Multi-Objective Bayesian Optimization
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
CALDA synergistically combines the principles of contrastive learning and adversarial learning to robustly support multi-source UDA (MS-UDA) for time series data.
Bayesian Optimization over Hybrid Spaces
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
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.
Mercer Features for Efficient Combinatorial Bayesian Optimization
In this paper, we propose an efficient approach referred as Mercer Features for Combinatorial Bayesian Optimization (MerCBO).
Optimizing Discrete Spaces via Expensive Evaluations: A Learning to Search Framework
We consider the problem of optimizing expensive black-box functions over discrete spaces (e. g., sets, sequences, graphs).
Multi-Fidelity Multi-Objective Bayesian Optimization: An Output Space Entropy Search Approach
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
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
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
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.
Scalable Combinatorial Bayesian Optimization with Tractable Statistical models
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
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
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.
An Energy-Aware Online Learning Framework for Resource Management in Heterogeneous Platforms
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.
One-Shot Induction of Generalized Logical Concepts via Human Guidance
First, we define a distance measure between candidate concept representations that improves the efficiency of search for target concept and generalization.
Max-value Entropy Search for Multi-Objective Bayesian Optimization
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.
Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach
Deep neural networks have seen tremendous success for different modalities of data including images, videos, and speech.
Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning
Our results show that active learning allows us to discover significantly more anomalies than state-of-the-art unsupervised baselines, our batch active learning algorithm discovers diverse anomalies, and our algorithms under the streaming-data setup are competitive with the batch setup.
Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems
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
Human analysts that use anomaly detection systems in practice want to retain the use of simple and explainable global anomaly detectors.
Active Anomaly Detection via Ensembles
First, we present an important insight into how anomaly detector ensembles are naturally suited for active learning.
Learning Scripts as Hidden Markov Models
Scripts have been proposed to model the stereotypical event sequences found in narratives.
Machine Learning and Manycore Systems Design: A Serendipitous Symbiosis
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.
Towards Problem Solving Agents that Communicate and Learn
Agents that communicate back and forth with humans to help them execute non-linguistic tasks are a long sought goal of AI.
HC-Search for Structured Prediction in Computer Vision
The mainstream approach to structured prediction problems in computer vision is to learn an energy function such that the solution minimizes that function.
