arXiv research

Paper formulates mutual information optimal control for discrete-time systems.

Fishnets improve set and graph learning with scalable, robust aggregation.

We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitable framework for encouraging explorations in such hierarchical networks. A natural utilization of this framework is an adversarial setting, w…

Geometric structure reveals optimal investment and hedging products.

In this paper, we address the problem of adaptive learning for autoregressive moving average (ARMA) model in the quaternion domain. By transforming the original learning problem into a full information optimization task without explicit noise terms, and then solving the optimization problem using the gradient descent a…

A new mutual information optimization method using self-supervised binary contrastive learning.

As Deep Learning (DL) models have been increasingly used in latency-sensitive applications, there has been a growing interest in improving their response time. An important venue for such improvement is to profile the execution of these models and characterize their performance to identify possible optimization opportu…

Recently several methods were proposed for sparse optimization which make careful use of second-order information [10, 28, 16, 3] to improve local convergence rates. These methods construct a composite quadratic approximation using Hessian information, optimize this approximation using a first-order method, such as coo…

In this paper, we provide an approach to clustering relational matrices whose entries correspond to either similarities or dissimilarities between objects. Our approach is based on the value of information, a parameterized, information-theoretic criterion that measures the change in costs associated with changes in inf…

Second-order optimizers retain residual information after data deletion, affecting machine unlearning.

Study shows optimal RL with transition look-ahead is NP-hard for $\ell \geq 2$.

We propose a Bayesian optimization algorithm for objective functions that are sums or integrals of expensive-to-evaluate functions, allowing noisy evaluations. These objective functions arise in multi-task Bayesian optimization for tuning machine learning hyperparameters, optimization via simulation, and sequential des…

StreamBP optimally detects communities in growing networks.

CausalCOMRL improves RL task representations by integrating causal relationships, enhancing generalizability.

A new method optimizes complex engineering designs under uncertainty efficiently.

User-based attribute information, such as age and gender, is usually considered as user privacy information. It is difficult for enterprises to obtain user-based privacy attribute information. However, user-based privacy attribute information has a wide range of applications in personalized services, user behavior anal…

New insights link RLHF and contrastive learning for better model alignment.

The paper constructs denoisers that recover the Brenier map from higher-order score functions.

Novel network model estimates mixed-membership structure with covariate information.

Recurrent networks learn beliefs from history in partially observable environments.

We consider the problem of global optimization of an unknown non-convex smooth function with zeroth-order feedback. In this setup, an algorithm is allowed to adaptively query the underlying function at different locations and receives noisy evaluations of function values at the queried points (i.e. the algorithm has ac…

We investigate the problem of estimating the causal effect of a treatment on individual subjects from observational data, this is a central problem in various application domains, including healthcare, social sciences, and online advertising. Within the Neyman Rubin potential outcomes model, we use the Kullback Leibler…

Attention to entropic communication improves message decoding and cooperation.

Investigates optimal portfolio strategies in markets with latent side information.

We analyse the optimal exercise of an executive stock option (ESO) written on a stock whose drift parameter falls to a lower value at a change point, an exponentially distributed random time independent of the Brownian motion driving the stock. Two agents, who do not trade the stock, have differing information on the c…

Cross-entropy loss linked to metric learning, outperforming complex pairwise losses.

Study shows current simulations are insufficient for optimal neural network training in cosmology.