Measurement Scheduling for ICU Patients with Offline Reinforcement Learning
Scheduling laboratory tests for ICU patients presents a significant challenge. Studies show that 20-40% of lab tests ordered in the ICU are redundant and could be eliminated without compromising...
View ArticleRandom Geometric Graph Alignment with Graph Neural Networks
We characterize the performance of graph neural networks for graph alignment problems in the presence of vertex feature information. More specifically, given two graphs that are independent...
View ArticleSumming Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
How do transformer-based large language models (LLMs) store and retrieve knowledge? We focus on the most basic form of this task -- factual recall, where the model is tasked with explicitly surfacing...
View ArticleODIN: Disentangled Reward Mitigates Hacking in RLHF
In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs. A well-formatted, verbose but less helpful...
View ArticleA Theoretical Analysis of Nash Learning from Human Feedback under General...
Reinforcement Learning from Human Feedback (RLHF) learns from the preference signal provided by a probabilistic preference model, which takes a prompt and two responses as input, and produces a score...
View ArticleHyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node...
Hypergraphs are marked by complex topology, expressing higher-order interactions among multiple entities with hyperedges. Lately, hypergraph-based deep learning methods to learn informative data...
View ArticleTraining Heterogeneous Client Models using Knowledge Distillation in...
Federated Learning (FL) is an emerging machine learning paradigm that enables the collaborative training of a shared global model across distributed clients while keeping the data decentralized. Recent...
View ArticlePower Transformer Fault Prediction Based on Knowledge Graphs
In this paper, we address the challenge of learning with limited fault data for power transformers. Traditional operation and maintenance tools lack effective predictive capabilities for potential...
View ArticleCan Tree Based Approaches Surpass Deep Learning in Anomaly Detection? A...
Detection of anomalous situations for complex mission-critical systems holds paramount importance when their service continuity needs to be ensured. A major challenge in detecting anomalies from the...
View ArticlePhysics-Informed Neural Networks with Hard Linear Equality Constraints
Surrogate modeling is used to replace computationally expensive simulations. Neural networks have been widely applied as surrogate models that enable efficient evaluations over complex physical...
View ArticleDIMON: Learning Solution Operators of Partial Differential Equations on a...
The solution of a PDE over varying initial/boundary conditions on multiple domains is needed in a wide variety of applications, but it is computationally expensive if the solution is computed de novo...
View ArticleThe Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular...
The precise prediction of molecular properties is essential for advancements in drug development, particularly in virtual screening and compound optimization. The recent introduction of numerous deep...
View ArticleDepth Separations in Neural Networks: Separating the Dimension from the Accuracy
We prove an exponential separation between depth 2 and depth 3 neural networks, when approximating an $\mathcal{O}(1)$-Lipschitz target function to constant accuracy, with respect to a distribution...
View ArticleTowards Generalized Inverse Reinforcement Learning
This paper studies generalized inverse reinforcement learning (GIRL) in Markov decision processes (MDPs), that is, the problem of learning the basic components of an MDP given observed behavior...
View ArticleGenSTL: General Sparse Trajectory Learning via Auto-regressive Generation of...
Trajectories are sequences of timestamped location samples. In sparse trajectories, the locations are sampled infrequently; and while such trajectories are prevalent in real-world settings, they are...
View ArticleRethinking Graph Masked Autoencoders through Alignment and Uniformity
Self-supervised learning on graphs can be bifurcated into contrastive and generative methods. Contrastive methods, also known as graph contrastive learning (GCL), have dominated graph self-supervised...
View ArticleTowards Fast Stochastic Sampling in Diffusion Generative Models
Diffusion models suffer from slow sample generation at inference time. Despite recent efforts, improving the sampling efficiency of stochastic samplers for diffusion models remains a promising...
View ArticleMore Benefits of Being Distributional: Second-Order Bounds for Reinforcement...
In this paper, we prove that Distributional Reinforcement Learning (DistRL), which learns the return distribution, can obtain second-order bounds in both online and offline RL in general settings with...
View ArticleThe Implicit Bias of Gradient Noise: A Symmetry Perspective
We characterize the learning dynamics of stochastic gradient descent (SGD) when continuous symmetry exists in the loss function, where the divergence between SGD and gradient descent is dramatic. We...
View ArticleGSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph...
Graph invariant learning (GIL) has been an effective approach to discovering the invariant relationships between graph data and its labels for different graph learning tasks under various distribution...
View Article