arXiv research

New bounds show limitations of sample-wise information-theoretic generalization.

In this paper, we study the information-theoretic limits of learning the structure of Bayesian networks (BNs), on discrete as well as continuous random variables, from a finite number of samples. We show that the minimum number of samples required by any procedure to recover the correct structure grows as $Ω(m)$ and $Ω…

New bounds improve generalization in learning scenarios.

Information-theoretic Bayesian optimisation techniques have demonstrated state-of-the-art performance in tackling important global optimisation problems. However, current information-theoretic approaches require many approximations in implementation, introduce often-prohibitive computational overhead and limit the choi…

Study sets limits for detecting a subhypergraph in uniform hypergraphs.

New research shows existing information-theoretic methods can't establish minimax rates for gradient descent in stochastic convex optimization.

Sharp asymptotics derived for phase retrieval and compressed sensing with random generative priors.

Neural networks learn complex functions efficiently near information-theoretic limits.

Information-theoretic bounded rationality describes utility-optimizing decision-makers whose limited information-processing capabilities are formalized by information constraints. One of the consequences of bounded rationality is that resource-limited decision-makers can join together to solve decision-making problems …

Study reveals limits of detecting local geometry in random graphs.

We analyze the necessary number of samples for sparse vector recovery in a noisy linear prediction setup. This model includes problems such as linear regression and classification. We focus on structured graph models. In particular, we prove that sufficient number of samples for the weighted graph model proposed by Heg…

We solve matrix denoising with both row and column correlations, setting limits and designing optimal methods.

Paper analyzes ECE bias and provides bounds for its estimation.

In this paper, we develop a framework to obtain graph abstractions for decision-making by an agent where the abstractions emerge as a function of the agent's limited computational resources. We discuss the connection of the proposed approach with information-theoretic signal compression, and formulate a novel optimizat…

The stochastic block model (SBM) is a random graph model with different group of vertices connecting differently. It is widely employed as a canonical model to study clustering and community detection, and provides a fertile ground to study the information-theoretic and computational tradeoffs that arise in combinatori…

Improved robust regression with clean covariates achieves better rates than Huber's model.

We analyze the information-theoretic limits for the recovery of node labels in several network models. This includes the Stochastic Block Model, the Exponential Random Graph Model, the Latent Space Model, the Directed Preferential Attachment Model, and the Directed Small-world Model. For the Stochastic Block Model, the…

We study optimal estimation for sparse principal component analysis when the number of non-zero elements is small but on the same order as the dimension of the data. We employ approximate message passing (AMP) algorithm and its state evolution to analyze what is the information theoretically minimal mean-squared error …

Unified framework improves meta-learning generalization bounds.

Unified information-theoretic objectives for training deep neural networks.

EDL discovers state-covering skills without relying on task rewards.

Study information limits for community detection in sub-hypergraphs.

The support recovery problem consists of determining a sparse subset of variables that is relevant in generating a set of observations. In this paper, we study the support recovery problem in the phase retrieval model consisting of noisy phaseless measurements, which arises in a diverse range of settings such as optica…

Neural network learns low-dimensional polynomials with SGD near information-theoretic limit.

Spectral clustering achieves strong consistency in the stochastic block model under certain conditions.

This paper improves DNN generalization by accurately estimating mutual information.

Study on maximizing submodular functions with limited updates, achieving tight bounds and poly-time algorithms.

Bounded rationality, that is, decision-making and planning under resource limitations, is widely regarded as an important open problem in artificial intelligence, reinforcement learning, computational neuroscience and economics. This paper offers a consolidated presentation of a theory of bounded rationality based on i…

Why are classifiers in high dimension vulnerable to "adversarial" perturbations? We show that it is likely not due to information theoretic limitations, but rather it could be due to computational constraints. First we prove that, for a broad set of classification tasks, the mere existence of a robust classifier implie…

Exact pairwise ranking is achievable but not possible under noisy comparisons.

We consider the problem of Gaussian mixture clustering in the high-dimensional limit where the data consists of $m$ points in $n$ dimensions, $n,m \rightarrow \infty$ and $α= m/n$ stays finite. Using exact but non-rigorous methods from statistical physics, we determine the critical value of $α$ and the distance between…

A new method clusters intersecting lines using hypergraphs.

New confidence intervals improve treatment effect estimation in randomized experiments.

Information theoretic measures (e.g. the Kullback Liebler divergence and Shannon mutual information) have been used for exploring possibly nonlinear multivariate dependencies in high dimension. If these dependencies are assumed to follow a Markov factor graph model, this exploration process is called structure discover…

The paper uses information theory to find limits of feedback control systems.

Study on matching nodes between graphs to preserve edges, focusing on limits and algorithms.

The paper extends Thompson Sampling to infinite action spaces using information theory.

New algorithm achieves strong consistency in binary non-uniform hypergraph classification.

In order to choose a neural network architecture that will be effective for a particular modeling problem, one must understand the limitations imposed by each of the potential options. These limitations are typically described in terms of information theoretic bounds, or by comparing the relative complexity needed to a…

In this paper, we study the information-theoretic limits of community detection in the symmetric two-community stochastic block model, with intra-community and inter-community edge probabilities $\frac{a}{n}$ and $\frac{b}{n}$ respectively. We consider the sparse setting, in which $a$ and $b$ do not scale with $n$, and…

The paper proposes a framework for information-theoretic predictive uncertainty measures.

Lower bounds show many sampling algorithms need many gradient queries.

A novel Q-learning algorithm connects information theory to MPC, improving control tasks.

Neural node embeddings have recently emerged as a powerful representation for supervised learning tasks involving graph-structured data. We leverage this recent advance to develop a novel algorithm for unsupervised community discovery in graphs. Through extensive experimental studies on simulated and real-world data, w…

New model improves community detection in networks with strong assortativity.

New compression theory justifies model pruning for neural networks.

Bounded rationality investigates utility-optimizing decision-makers with limited information-processing power. In particular, information theoretic bounded rationality models formalize resource constraints abstractly in terms of relative Shannon information, namely the Kullback-Leibler Divergence between the agents' pr…

New approach uses contrastive learning for better wireless power control.