Latent Space Translation via Semantic Alignment
While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible. Towards a better...
View ArticleFinite Time Analysis of Constrained Actor Critic and Constrained Natural...
Actor Critic methods have found immense applications on a wide range of Reinforcement Learning tasks especially when the state-action space is large. In this paper, we consider actor critic and natural...
View ArticleFederated Learning of Large Language Models with Parameter-Efficient Prompt...
Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. However, the training process of Large Language Models (LLMs) generally incurs the update...
View ArticlepFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning
Federated learning (FL) is an emerging machine learning paradigm in which a central server coordinates multiple participants (clients) collaboratively to train on decentralized data. In practice, FL...
View ArticleStatistical inference using machine learning and classical techniques based...
Accumulated Local Effects (ALE) is a model-agnostic approach for global explanations of the results of black-box machine learning (ML) algorithms. There are at least three challenges with conducting...
View ArticleMixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space
Recent advances in tabular data generation have greatly enhanced synthetic data quality. However, extending diffusion models to tabular data is challenging due to the intricately varied distributions...
View ArticleDiscerning Temporal Difference Learning
Temporal difference learning (TD) is a foundational concept in reinforcement learning (RL), aimed at efficiently assessing a policy's value function. TD($\lambda$), a potent variant, incorporates a...
View ArticleRobust Angular Synchronization via Directed Graph Neural Networks
The angular synchronization problem aims to accurately estimate (up to a constant additive phase) a set of unknown angles $\theta_1, \dots, \theta_n\in[0, 2\pi)$ from $m$ noisy measurements of their...
View ArticleHierarchical Multi-Marginal Optimal Transport for Network Alignment
Finding node correspondence across networks, namely multi-network alignment, is an essential prerequisite for joint learning on multiple networks. Despite great success in aligning networks in pairs,...
View ArticlePGraphDTA: Improving Drug Target Interaction Prediction using Protein...
Developing and discovering new drugs is a complex and resource-intensive endeavor that often involves substantial costs, time investment, and safety concerns. A key aspect of drug discovery involves...
View ArticleImproved prediction of ligand-protein binding affinities by meta-modeling
The accurate screening of candidate drug ligands against target proteins through computational approaches is of prime interest to drug development efforts. Such virtual screening depends in part on...
View Article$(\epsilon, u)$-Adaptive Regret Minimization in Heavy-Tailed Bandits
Heavy-tailed distributions naturally arise in several settings, from finance to telecommunications. While regret minimization under subgaussian or bounded rewards has been widely studied, learning with...
View ArticleUniversality of almost periodicity in bounded discrete time series
We consider bounded discrete time series. From its statistical feature, without any use of the Fourier transform, we find a suitable almost periodic function which approximates the corresponding time...
View ArticleIntrinsic Biologically Plausible Adversarial Training
Artificial Neural Networks (ANNs) trained with Backpropagation (BP) excel in different daily tasks but have a dangerous vulnerability: inputs with small targeted perturbations, also known as...
View ArticleUniversal Sleep Decoder: Aligning awake and sleep neural representation...
Decoding memory content from brain activity during sleep has long been a goal in neuroscience. While spontaneous reactivation of memories during sleep in rodents is known to support memory...
View ArticleClass Incremental Learning via Likelihood Ratio Based Task Prediction
Class incremental learning (CIL) is a challenging setting of continual learning, which learns a series of tasks sequentially. Each task consists of a set of unique classes. The key feature of CIL is...
View ArticleMarket-GAN: Adding Control to Financial Market Data Generation with Semantic...
Financial simulators play an important role in enhancing forecasting accuracy, managing risks, and fostering strategic financial decision-making. Despite the development of financial market simulation...
View ArticleZero-Shot Robustification of Zero-Shot Models
Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are vulnerable to...
View ArticleSolving Non-Rectangular Reward-Robust MDPs via Frequency Regularization
In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set. By targeting maximal return under the most adversarial model from...
View ArticleAccuracy Improvement in Differentially Private Logistic Regression: A...
Machine learning (ML) models can memorize training datasets. As a result, training ML models over private datasets can lead to the violation of individuals' privacy. Differential privacy (DP) is a...
View Article