Search Results for author:
Found 21 papers, 4 papers with code
Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute
This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute.
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
We present MM-Eureka, a multimodal reasoning model that successfully extends large-scale rule-based reinforcement learning (RL) to multimodal reasoning.
If Multi-Agent Debate is the Answer, What is the Question?
Multi-agent debate (MAD) has emerged as a promising approach to enhance the factual accuracy and reasoning quality of large language models (LLMs) by engaging multiple agents in iterative discussions during inference.
Graph Feedback Bandits on Similar Arms: With and Without Graph Structures
In this paper, we study the stochastic multi-armed bandit problem with graph feedback.
Online Preference Alignment for Language Models via Count-based Exploration
Then, we reformulate our objective to direct preference optimization with an exploration term, where the UCB-term can be converted to a count-based exploration bonus.
Community Detection for Contextual-LSBM: Theoretical Limitations of Misclassification Rate and Efficient Algorithms
The integration of network information and node attribute information has recently gained significant attention in the community detection literature.
Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models
Specifically, by appropriately defining \emph{structure noise} and \emph{feature noise} in graphs, we show that graph attention mechanisms can enhance classification performance when structure noise exceeds feature noise.
A Fast Convergence Theory for Offline Decision Making
This paper proposes the first generic fast convergence result in general function approximation for offline decision making problems, which include offline reinforcement learning (RL) and off-policy evaluation (OPE) as special cases.
Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning
To address this problem, our work builds upon the investigation of successor representations for task generalization in online RL and extends the framework to incorporate offline-to-online learning.
Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning
Finally, we extend Reg-MAIDS to multi-player general-sum MGs and prove that it can learn either the Nash equilibrium or coarse correlated equilibrium in a sample efficient manner.
Community Detection in the Multi-View Stochastic Block Model
This paper considers the problem of community detection on multiple potentially correlated graphs from an information-theoretical perspective.
Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms
Theoretical analyses show that our algorithm succeeds with high probability as long as the sample probability exceeds the aforementioned threshold, and this theoretical result is further validated by synthetic experiments.
MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World
The regularization terms further enhance the practicality of the generated APs in the physical domain.
Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems
We first argue that the MSE minimization approach is equivalent to a conditional entropy learning problem, and then propose a mutual information learning formulation for solving regression problems by using a reparameterization technique.
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
Deep learning systems have been reported to acheive state-of-the-art performances in many applications, and one of the keys for achieving this is the existence of well trained classifiers on benchmark datasets which can be used as backbone feature extractors in downstream tasks.
Mutual Information Learned Classifiers: an Information-theoretic Viewpoint of Training Deep Learning Classification Systems
Deep learning systems have been reported to achieve state-of-the-art performances in many applications, and a key is the existence of well trained classifiers on benchmark datasets.
Exact Recovery in the General Hypergraph Stochastic Block Model
This paper investigates fundamental limits of exact recovery in the general d-uniform hypergraph stochastic block model (d-HSBM), wherein n nodes are partitioned into k disjoint communities with relative sizes (p1,..., pk).
MC2G: An Efficient Algorithm for Matrix Completion with Social and Item Similarity Graphs
In this paper, we design and analyze MC2G (Matrix Completion with 2 Graphs), an algorithm that performs matrix completion in the presence of social and item similarity graphs.
Optimal Change-Point Detection with Training Sequences in the Large and Moderate Deviations Regimes
This paper investigates a novel offline change-point detection problem from an information-theoretic perspective.
Community Detection and Matrix Completion with Social and Item Similarity Graphs
We consider the problem of recovering a binary rating matrix as well as clusters of users and items based on a partially observed matrix together with side-information in the form of social and item similarity graphs.
Comparison among dimensionality reduction techniques based on Random Projection for cancer classification
FS followed by RP outperforms other combination methods in classification accuracy on most of the datasets.
