Search Results for author:
Found 62 papers, 4 papers with code
CiteQA@CLSciSumm 2020
In academic publications, citations are used to build context for a concept by highlighting relevant aspects from reference papers.
Investigation of English to Hindi Multimodal Neural Machine Translation using Transliteration-based Phrase Pairs Augmentation
Machine translation translates one natural language to another, a well-defined natural language processing task.
Program Evaluation with Remotely Sensed Outcomes
While traditional program evaluations typically rely on surveys to measure outcomes, certain economic outcomes such as living standards or environmental quality may be infeasible or costly to collect.
Provably Adaptive Average Reward Reinforcement Learning for Metric Spaces
We note that the existing notion of zooming dimension for average reward RL is defined in terms of policy coverings, and hence it can be huge when the policy class is rich even though the underlying MDP is simple, so that the regret upper bound is nearly $O(T)$.
Latent Representation Learning for Multimodal Brain Activity Translation
Neuroscience employs diverse neuroimaging techniques, each offering distinct insights into brain activity, from electrophysiological recordings such as EEG, which have high temporal resolution, to hemodynamic modalities such as fMRI, which have increased spatial precision.
Looking through the mind's eye via multimodal encoder-decoder networks
In this work, we explore the decoding of mental imagery from subjects using their fMRI measurements.
Downstream bias mitigation is all you need
The advent of transformer-based architectures and large language models (LLMs) have significantly advanced the performance of natural language processing (NLP) models.
Automatic Generation of Behavioral Test Cases For Natural Language Processing Using Clustering and Prompting
Recent work in behavioral testing for natural language processing (NLP) models, such as Checklist, is inspired by related paradigms in software engineering testing.
Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning
We study infinite-horizon average-reward reinforcement learning (RL) for Lipschitz MDPs and develop an algorithm PZRL that discretizes the state-action space adaptively and zooms in to promising regions of the "policy space" which seems to yield high average rewards.
On Learning for Ambiguous Chance Constrained Problems
When the DM has access to a set of distributions $\mathcal{U}$ such that $P$ is contained in $\mathcal{U}$, then the problem is known as the ambiguous chance-constrained problem \cite{erdougan2006ambiguous}.
Related Rhythms: Recommendation System To Discover Music You May Like
Machine Learning models are being utilized extensively to drive recommender systems, which is a widely explored topic today.
Finite Time Regret Bounds for Minimum Variance Control of Autoregressive Systems with Exogenous Inputs
Minimum variance controllers have been employed in a wide-range of industrial applications.
Kernel Ridge Regression Inference
We provide uniform inference and confidence bands for kernel ridge regression (KRR), a widely-used non-parametric regression estimator for general data types including rankings, images, and graphs.
Signed Graph Neural Networks: A Frequency Perspective
Graph convolutional networks (GCNs) and its variants are designed for unsigned graphs containing only positive links.
Quantifying Inherent Randomness in Machine Learning Algorithms
Among the different algorithms, randomness in model training causes larger variation for FFNNs compared to tree-based methods.
Understanding Metrics for Paraphrasing
This is not only because of the limitations in text generation capabilities but also due that to the lack of a proper definition of what qualifies as a paraphrase and corresponding metrics to measure how good it is.
Automatic Debiased Machine Learning for Dynamic Treatment Effects and General Nested Functionals
We extend the idea of automated debiased machine learning to the dynamic treatment regime and more generally to nested functionals.
Whittle Index based Q-Learning for Wireless Edge Caching with Linear Function Approximation
Using this structural result, we establish the indexability of our problem, and employ the Whittle index policy to minimize average latency.
Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems
We consider the problem of controlling an unknown stochastic linear system with quadratic costs - called the adaptive LQ control problem.
Generalized Kernel Ridge Regression for Long Term Causal Inference: Treatment Effects, Dose Responses, and Counterfactual Distributions
For long term dose responses, I prove uniform consistency with finite sample rates.
Nested Nonparametric Instrumental Variable Regression: Long Term, Mediated, and Time Varying Treatment Effects
We analyze adversarial estimators of nested NPIV, and provide sufficient conditions for efficient inference on the causal parameter.
Generalized Kernel Ridge Regression for Causal Inference with Missing-at-Random Sample Selection
I propose kernel ridge regression estimators for nonparametric dose response curves and semiparametric treatment effects in the setting where an analyst has access to a selected sample rather than a random sample; only for select observations, the outcome is observed.
Sequential Kernel Embedding for Mediated and Time-Varying Dose Response Curves
We propose simple nonparametric estimators for mediated and time-varying dose response curves based on kernel ridge regression.
Pruning Attention Heads of Transformer Models Using A* Search: A Novel Approach to Compress Big NLP Architectures
Our results indicate that the method could eliminate as much as 40% of the attention heads in the BERT transformer model with no loss in accuracy.
Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits
We call it the R(MA)^2B-UCB algorithm.
Inference of collective Gaussian hidden Markov models
We consider inference problems for a class of continuous state collective hidden Markov models, where the data is recorded in aggregate (collective) form generated by a large population of individuals following the same dynamics.
Causal Inference with Corrupted Data: Measurement Error, Missing Values, Discretization, and Differential Privacy
We propose a procedure for data cleaning, estimation, and inference with data cleaning-adjusted confidence intervals.
A Simple and General Debiased Machine Learning Theorem with Finite Sample Guarantees
Debiased machine learning is a meta algorithm based on bias correction and sample splitting to calculate confidence intervals for functionals, i. e. scalar summaries, of machine learning algorithms.
Self-interpretable Convolutional Neural Networks for Text Classification
We also study the impact of the complexity of the convolutional layers and the classification layers on the model performance.
Robustness Tests of NLP Machine Learning Models: Search and Semantically Replace
This paper proposes a strategy to assess the robustness of different machine learning models that involve natural language processing (NLP).
Kernel Ridge Riesz Representers: Generalization, Mis-specification, and the Counterfactual Effective Dimension
KRRR is an exact generalization of kernel ridge regression and kernel ridge balancing weights.
Some parametric tests based on sample spacings
The proposed tests provide alternative to similar tests based on simple spacings (i. e., $m=1$), that were proposed earlier in the literature.
Statistics Theory Statistics Theory 62F03, 62F05
Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers
In this paradigm, each worker maintains a local estimate of the optimal parameter vector, and iteratively updates it by waiting and averaging all estimates obtained from its neighbors, and then corrects it on the basis of its local dataset.
Low-Power Status Updates via Sleep-Wake Scheduling
We devise a low-complexity solution to solve this problem and prove that, for practical sensing times that are short, the solution is within a small gap from the optimum AoI performance.
Information Theory Information Theory
Learning Augmented Index Policy for Optimal Service Placement at the Network Edge
We pose the problem as a Markov decision process (MDP) in which the system state is given by describing, for each service, the number of customers that are currently waiting at the edge to obtain the service.
Adversarial Estimation of Riesz Representers
Many causal parameters are linear functionals of an underlying regression.
Kernel Methods for Unobserved Confounding: Negative Controls, Proxies, and Instruments
Negative control is a strategy for learning the causal relationship between treatment and outcome in the presence of unmeasured confounding.
Learning Hidden Markov Models from Aggregate Observations
This problem arises when only the population level counts of the number of individuals at each time step are available, from which one seeks to learn the individual hidden Markov model.
Reward Biased Maximum Likelihood Estimation for Reinforcement Learning
The Reward-Biased Maximum Likelihood Estimate (RBMLE) for adaptive control of Markov chains was proposed to overcome the central obstacle of what is variously called the fundamental "closed-identifiability problem" of adaptive control, the "dual control problem", or, contemporaneously, the "exploration vs. exploitation problem".
Unwrapping The Black Box of Deep ReLU Networks: Interpretability, Diagnostics, and Simplification
We propose the local linear profile plot and other visualization methods for interpretation and diagnostics, and an effective merging strategy for network simplification.
Filtering for Aggregate Hidden Markov Models with Continuous Observations
We consider a class of filtering problems for large populations where each individual is modeled by the same hidden Markov model (HMM).
Multi-Armed Bandits with Dependent Arms
We study a variant of the classical multi-armed bandit problem (MABP) which we call as Multi-Armed Bandits with dependent arms.
Kernel Methods for Causal Functions: Dose, Heterogeneous, and Incremental Response Curves
We propose estimators based on kernel ridge regression for nonparametric causal functions such as dose, heterogeneous, and incremental response curves.
Model Robustness with Text Classification: Semantic-preserving adversarial attacks
We propose algorithms to create adversarial attacks to assess model robustness in text classification problems.
A Partially Observable MDP Approach for Sequential Testing for Infectious Diseases such as COVID-19
In this paper, we show that the testing problem can be cast as a sequential learning-based resource allocation problem with constraints, where the input to the problem is provided by a time-varying social contact graph obtained through various contact tracing tools.
Incremental inference of collective graphical models
We consider incremental inference problems from aggregate data for collective dynamics.
Multi-marginal optimal transport and probabilistic graphical models
We study multi-marginal optimal transport problems from a probabilistic graphical model perspective.
Mather classes and conormal spaces of Schubert varieties in cominuscule spaces
We prove a type independent formula for the torus equivariant Mather class of a Schubert variety in $G/P$, and for a Schubert variety pulled back via the natural projection $G/Q \to G/P$.
Algebraic Geometry Combinatorics Representation Theory (MSC 2020) Primary: 14C17, 14M15, Secondary 32S60
Contextual Bandits with Side-Observations
We show that this asymptotically optimal regret is upper-bounded as $O\left(|\chi(\mathcal{G})|\log T\right)$, where $|\chi(\mathcal{G})|$ is the domination number of $\mathcal{G}$.
Improving Robustness via Risk Averse Distributional Reinforcement Learning
One major obstacle that precludes the success of reinforcement learning in real-world applications is the lack of robustness, either to model uncertainties or external disturbances, of the trained policies.
Distributional Reinforcement Learning
reinforcement-learning
+2
Inference with Aggregate Data: An Optimal Transport Approach
Consequently, the celebrated Sinkhorn/iterative scaling algorithm for multi-marginal optimal transport can be leveraged together with the standard belief propagation algorithm to establish an efficient inference scheme which we call Sinkhorn belief propagation (SBP).
Learning in Networked Control Systems
We design adaptive controller (learning rule) for a networked control system (NCS) in which data packets containing control information are transmitted across a lossy wireless channel.
Learning in Markov Decision Processes under Constraints
In order to measure the performance of a reinforcement learning algorithm that satisfies the average cost constraints, we define an $M+1$ dimensional regret vector that is composed of its reward regret, and $M$ cost regrets.
Sample-based Distributional Policy Gradient
It relies on the key idea of replacing the expected return with the return distribution, which captures the intrinsic randomness of the long term rewards.
Double Robustness for Complier Parameters and a Semiparametric Test for Complier Characteristics
We propose a semiparametric test to evaluate (i) whether different instruments induce subpopulations of compliers with the same observable characteristics on average, and (ii) whether compliers have observable characteristics that are the same as the full population on average.
Kernel Instrumental Variable Regression
Instrumental variable (IV) regression is a strategy for learning causal relationships in observational data.
Understand the dynamics of GANs via Primal-Dual Optimization
By developing new primal-dual optimization tools, we show that, with a proper stepsize choice, the widely used first-order iterative algorithm in training GANs would in fact converge to a stationary solution with a sublinear rate.
3D Deep Learning with voxelized atomic configurations for modeling atomistic potentials in complex solid-solution alloys
In this paper, we explore a deep convolutional neural-network based approach to develop the atomistic potential for such complex alloys to investigate materials for insights into controlling properties.
Physics-aware Deep Generative Models for Creating Synthetic Microstructures
The first model is a WGAN model that uses a finite number of training images to synthesize new microstructures that weakly satisfy the physical invariances respected by the original data.
De-Biased Machine Learning of Global and Local Parameters Using Regularized Riesz Representers
To achieve this property, we include the Riesz representer for the functional as an additional nuisance parameter.
Throughput Optimal Decentralized Scheduling of Multi-Hop Networks with End-to-End Deadline Constraints: II Wireless Networks with Interference
The key difference arises due to the fact that in our set-up the packets loose their utility once their "age" has crossed their deadline, thus making the task of optimizing timely throughput much more challenging than that of ensuring network stability.
Kiefer Wolfowitz Algorithm is Asymptotically Optimal for a Class of Non-Stationary Bandit Problems
We consider the problem of designing an allocation rule or an "online learning algorithm" for a class of bandit problems in which the set of control actions available at each time $s$ is a convex, compact subset of $\mathbb{R}^d$.
