Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective...
A significant challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies that attain optimal performance under different preferences. We introduce Iterated Pareto...
View ArticleMAGNETO: Edge AI for Human Activity Recognition -- Privacy and Personalization
Human activity recognition (HAR) is a well-established field, significantly advanced by modern machine learning (ML) techniques. While companies have successfully integrated HAR into consumer products,...
View ArticleGeoFormer: A Vision and Sequence Transformer-based Approach for Greenhouse...
Air pollution represents a pivotal environmental challenge globally, playing a major role in climate change via greenhouse gas emissions and negatively affecting the health of billions. However...
View ArticleExplainable Global Wildfire Prediction Models using Graph Neural Networks
Wildfire prediction has become increasingly crucial due to the escalating impacts of climate change. Traditional CNN-based wildfire prediction models struggle with handling missing oceanic data and...
View ArticleTowards Robust Car Following Dynamics Modeling via Blackbox Models:...
The selection of the target variable is important while learning parameters of the classical car following models like GIPPS, IDM, etc. There is a vast body of literature on which target variable is...
View ArticleAn attempt to generate new bridge types from latent space of denoising...
Use denoising diffusion implicit model for bridge-type innovation. The process of adding noise and denoising to an image can be likened to the process of a corpse rotting and a detective restoring the...
View ArticleTowards Quantifying the Preconditioning Effect of Adam
There is a notable dearth of results characterizing the preconditioning effect of Adam and showing how it may alleviate the curse of ill-conditioning -- an issue plaguing gradient descent (GD). In this...
View ArticleDecoupling Learning and Decision-Making: Breaking the $\mathcal{O}(\sqrt{T})$...
Online linear programming plays an important role in both revenue management and resource allocation, and recent research has focused on developing efficient first-order online learning algorithms....
View ArticleEchoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential...
We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks. The proposed...
View ArticleFuture Prediction Can be a Strong Evidence of Good History Representation in...
Learning a good history representation is one of the core challenges of reinforcement learning (RL) in partially observable environments. Recent works have shown the advantages of various auxiliary...
View ArticleRethinking the Capacity of Graph Neural Networks for Branching Strategy
Graph neural networks (GNNs) have been widely used to predict properties and heuristics of mixed-integer linear programs (MILPs) and hence accelerate MILP solvers. This paper investigates the capacity...
View ArticleSelf-Correcting Self-Consuming Loops for Generative Model Training
As synthetic data becomes higher quality and proliferates on the internet, machine learning models are increasingly trained on a mix of human- and machine-generated data. Despite the successful stories...
View ArticleRefined Sample Complexity for Markov Games with Independent Linear Function...
Markov Games (MG) is an important model for Multi-Agent Reinforcement Learning (MARL). It was long believed that the "curse of multi-agents" (i.e., the algorithmic performance drops exponentially with...
View ArticleThe Relevance Feature and Vector Machine for health applications
This paper presents the Relevance Feature and Vector Machine (RFVM), a novel model that addresses the challenges of the fat-data problem when dealing with clinical prospective studies. The fat-data...
View ArticleUsing Large Language Models to Automate and Expedite Reinforcement Learning...
We present LARL-RM (Large language model-generated Automaton for Reinforcement Learning with Reward Machine) algorithm in order to encode high-level knowledge into reinforcement learning using...
View ArticleFast UCB-type algorithms for stochastic bandits with heavy and super heavy...
In this study, we propose a new method for constructing UCB-type algorithms for stochastic multi-armed bandits based on general convex optimization methods with an inexact oracle. We derive the regret...
View ArticleUnderstanding the Training Speedup from Sampling with Approximate Losses
It is well known that selecting samples with large losses/gradients can significantly reduce the number of training steps. However, the selection overhead is often too high to yield any meaningful...
View Article$L^*LM$: Learning Automata from Examples using Natural Language Oracles
Expert demonstrations have proven an easy way to indirectly specify complex tasks. Recent algorithms even support extracting unambiguous formal specifications, e.g. deterministic finite automata (DFA),...
View ArticleA Tale of Tails: Model Collapse as a Change of Scaling Laws
As AI model size grows, neural scaling laws have become a crucial tool to predict the improvements of large models when increasing capacity and the size of original (human or natural) training data....
View ArticleDistilling Symbolic Priors for Concept Learning into Neural Networks
Humans can learn new concepts from a small number of examples by drawing on their inductive biases. These inductive biases have previously been captured by using Bayesian models defined over symbolic...
View Article