arXiv research

New MD algorithms using Tempesta logarithms for machine learning.

New algorithm for sequential off-policy learning improves performance over batch methods.

Recently, prediction markets have shown considerable promise for developing flexible mechanisms for machine learning. In this paper, agents with isoelastic utilities are considered. It is shown that the costs associated with homogeneous markets of agents with isoelastic utilities produce equilibrium prices correspondin…

AdaptOn achieves logarithmic regret in adaptive control of unknown partially observable linear systems.

New algorithms solve convex-concave problems faster than previous methods.

Study nonparametric contextual bandits with batched updates, achieving optimal regret.

In this paper, a Bayesian inference technique based on Taylor series approximation of the logarithm of the likelihood function is presented. The proposed approximation is devised for the case, where the prior distribution belongs to the exponential family of distributions. The logarithm of the likelihood function is li…

Paper proves multiplicative weight updates can train neural networks without learning rate tuning.

This work analyzes how often to update the target network in Q-learning.

Algorithm optimizes quantized isotonic regression with log-linear time updates.

Quantum RL algorithm achieves logarithmic regret for exploration.

Paper proposes FedQ-Advantage for federated Q-learning with near-optimal regret and low communication cost.

AIHT improves online high-dimensional quantile regression by separating support discovery and refinement.

Algorithm identifies Pareto front using multiple context directions and reuses exploration samples.

A novel method to propagate uncertainty through the soft-thresholding nonlinearity is proposed in this paper. At every layer the current distribution of the target vector is represented as a spike and slab distribution, which represents the probabilities of each variable being zero, or Gaussian-distributed. Using the p…

Two algorithms learn Gaussian graphical models from Glauber dynamics trajectories, achieving optimal performance.

Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been observed that when using large batch sizes there is a persistent degradation in genera…

This survey consists of two parts. Part 1 is devoted to amoebas. These are images of algebraic subvarieties in the complex torus under the logarithmic moment map. The amoebas have essentially piecewise-linear shape if viewed at large. Furthermore, they degenerate to certain piecewise-linear objects called tropical vari…

Bayesian inference improved with classifier-based misspecification detection and tempering.

Study shows memory needs grow with task sequence length in continual learning.

Deep density methods improve filtering in high-dimensional systems.

We consider the problem of reconstructing a low rank matrix from a subset of its entries and analyze two variants of the so-called Alternating Minimization algorithm, which has been proposed in the past. We establish that when the underlying matrix has rank $r=1$, has positive bounded entries, and the graph $\mathcal{G…

Algorithm samples from online log-concave distributions efficiently.

This work broadens calibeating to various proper losses using Bregman divergence.

Study examines sample complexity for RL with safety constraints.

This work generalizes calibeating for a broader range of proper losses using Bregman divergence.

In this paper, we propose an information-theoretic exploration strategy for stochastic, discrete multi-armed bandits that achieves optimal regret. Our strategy is based on the value of information criterion. This criterion measures the trade-off between policy information and obtainable rewards. High amounts of policy …

In this paper, we introduce the notions of logarithmic Poisson structure and logarithmic principal Poisson structure; we prove that the latter induces a representation by logarithmic derivation of the module of logarithmic Kahler differentials; therefore, it induces a differential complex from which we derive the notio…

Algorithm reduces regret in restless multi-armed bandits by adaptively sequencing arm choices.

Optimizes variational inference for dynamic network models.

We develop a sequential low-complexity inference procedure for Dirichlet process mixtures of Gaussians for online clustering and parameter estimation when the number of clusters are unknown a-priori. We present an easily computable, closed form parametric expression for the conditional likelihood, in which hyperparamet…

Study rigidity by logarithmic capacity and related functions.

Study excess logarithmic residues for foliations to bound invariant hypersurfaces and test log canonicity.

Study real logarithms of semi-simple matrices, focusing on differential structure.

Logarithmic connections on principal bundles over normal varieties are studied.

Introduces logarithmic Cartan geometry on complex manifolds with singularities.

We present a new method to solve certain $\bar{\partial}$-equations for logarithmic differential forms by using harmonic integral theory for currents on Kahler manifolds. The result can be considered as a $\bar{\partial}$-lemma for logarithmic forms. As applications, we generalize the result of Deligne about closedness…

Local logarithmic Brunn-Minkowski holds for zonoids.

ZDP detects drift in large language models without labels, proving key theorems and metrics.

Gradient filters track moving parameters under noisy data and misspecification.

New framework for logarithmically divergent integrals on manifolds with corners.

Directly proves logarithmic systolic growth for all hyperbolic surfaces.

Logarithmic separation profile in hyperbolic groups shows hierarchical structure.

Paper uses ABP method to prove logarithmic Sobolev inequalities on curved spaces.

Investment and consumption strategy optimized under uncertain conditions.

The paper constructs a Saito basis for a specific class of divisors and applies it to logarithmic Poisson geometry.

Thompson Sampling, one of the oldest heuristics for solving multi-armed bandits, has recently been shown to demonstrate state-of-the-art performance. The empirical success has led to great interests in theoretical understanding of this heuristic. In this paper, we approach this problem in a way very different from exis…

Extended logarithm for solvable elements in mapping class groups.