Outlier-Aware Training for Low-Bit Quantization of Structural...
Lightweight design of Convolutional Neural Networks (CNNs) requires co-design efforts in the model architectures and compression techniques. As a novel design paradigm that separates training and...
View ArticleImproving LSH via Tensorized Random Projection
Locality sensitive hashing (LSH) is a fundamental algorithmic toolkit used by data scientists for approximate nearest neighbour search problems that have been used extensively in many large scale data...
View ArticlePASOA- PArticle baSed Bayesian Optimal Adaptive design
We propose a new procedure named PASOA, for Bayesian experimental design, that performs sequential design optimization by simultaneously providing accurate estimates of successive posterior...
View ArticleEffort and Size Estimation in Software Projects with Large Language...
The advancement of Large Language Models (LLM) has also resulted in an equivalent proliferation in its applications. Software design, being one, has gained tremendous benefits in using LLMs as an...
View ArticleNatural Language Reinforcement Learning
Reinforcement Learning (RL) has shown remarkable abilities in learning policies for decision-making tasks. However, RL is often hindered by issues such as low sample efficiency, lack of...
View ArticleA hybrid iterative method based on MIONet for PDEs: Theory and numerical...
We propose a hybrid iterative method based on MIONet for PDEs, which combines the traditional numerical iterative solver and the recent powerful machine learning method of neural operator, and further...
View ArticleX-LoRA: Mixture of Low-Rank Adapter Experts, a Flexible Framework for Large...
We report a mixture of expert strategy to create fine-tuned large language models using a deep layer-wise token-level approach based on low-rank adaptation (LoRA). Starting with a set of pre-trained...
View ArticleResampling methods for Private Statistical Inference
We consider the task of constructing confidence intervals with differential privacy. We propose two private variants of the non-parametric bootstrap, which privately compute the median of the results...
View ArticleLearning by Watching: A Review of Video-based Learning Approaches for Robot...
Robot learning of manipulation skills is hindered by the scarcity of diverse, unbiased datasets. While curated datasets can help, challenges remain in generalizability and real-world transfer....
View ArticleNext-Generation Teleophthalmology: AI-enabled Quality Assessment Aiding...
Blindness and other eye diseases are a global health concern, particularly in low- and middle-income countries like India. In this regard, during the COVID-19 pandemic, teleophthalmology became a...
View ArticleOn the Complexity of First-Order Methods in Stochastic Bilevel Optimization
We consider the problem of finding stationary points in Bilevel optimization when the lower-level problem is unconstrained and strongly convex. The problem has been extensively studied in recent years;...
View ArticleSpeech Rhythm-Based Speaker Embeddings Extraction from Phonemes and Phoneme...
This paper proposes a speech rhythm-based method for speaker embeddings to model phoneme duration using a few utterances by the target speaker. Speech rhythm is one of the essential factors among...
View ArticleLearning the Expected Core of Strictly Convex Stochastic Cooperative Games
Reward allocation, also known as the credit assignment problem, has been an important topic in economics, engineering, and machine learning. An important concept in credit assignment is the core, which...
View ArticleDifferentially Private Range Queries with Correlated Input Perturbation
This work proposes a class of locally differentially private mechanisms for linear queries, in particular range queries, that leverages correlated input perturbation to simultaneously achieve...
View ArticleInstance-Level Safety-Aware Fidelity of Synthetic Data and Its Calibration
Modeling and calibrating the fidelity of synthetic data is paramount in shaping the future of safe and reliable self-driving technology by offering a cost-effective and scalable alternative to...
View ArticleSemi-Supervised Learning for Bilingual Lexicon Induction
We consider the problem of aligning two sets of continuous word representations, corresponding to languages, to a common space in order to infer a bilingual lexicon. It was recently shown that it is...
View ArticleQuantum Speedup for Spectral Approximation of Kronecker Products
Given its widespread application in machine learning and optimization, the Kronecker product emerges as a pivotal linear algebra operator. However, its computational demands render it an expensive...
View ArticleGeneralization Error of Graph Neural Networks in the Mean-field Regime
This work provides a theoretical framework for assessing the generalization error of graph classification tasks via graph neural networks in the over-parameterized regime, where the number of...
View ArticleGemini Goes to Med School: Exploring the Capabilities of Multimodal Large...
Large language models have the potential to be valuable in the healthcare industry, but it's crucial to verify their safety and effectiveness through rigorous evaluation. For this purpose, we...
View ArticleAn Optimization Framework for Processing and Transfer Learning for the Brain...
Tumor segmentation from multi-modal brain MRI images is a challenging task due to the limited samples, high variance in shapes and uneven distribution of tumor morphology. The performance of automated...
View Article