arXiv research

Enhanced Lion optimizer CLion improves generalization with lower error.

Cautious Weight Decay modifies weight decay for better optimization.

Distributed Lion optimizes large model training by reducing communication costs.

Lion optimizer performs well in training AI models with memory efficiency.

LION generates high-quality 3D shapes using hierarchical latent diffusion models.

Unified view of Lion and Muon as Stochastic Frank-Wolfe methods.

This work uses Lasry-Lions envelopes to solve nonconvex optimization problems.

New optimizers improve stock market forecasting accuracy.

Muon optimizer improves deep learning with spectral norm constraints.

CARL safely adapts RL agents for safety-critical tasks.

Establishes a Lorentzian Lasry-Lions regularization theorem for functions on globally hyperbolic spacetimes.

A technique identifies memoryless algorithms approximating memory-dependent optimization methods.

We build a model using Gaussian processes to infer a spatio-temporal vector field from observed agent trajectories. Significant landmarks or influence points in agent surroundings are jointly derived through vector calculus operations that indicate presence of sources and sinks. We evaluate these influence points by us…

Two strategies extend multi-label chaining for imprecise probability estimates.

Most classifiers operate by selecting the maximum of an estimate of the conditional distribution $p(y|x)$ where $x$ stands for the features of the instance to be classified and $y$ denotes its label. This often results in a {\em hubristic bias}: overconfidence in the assignment of a definite label. Usually, the observa…

Confidential Guardian prevents model abstention from being used to discriminate.

We have carried out simulations of a financial model of the firm to analyse the validity of the concept of Trade on Equity in dynamics. The results exhibit the ability of the borrowing policy connected to a cautious dividend distribution to inject chaos into the profit motion. The 3D system built with the van der Pol's…

SDF-Bayes finds safe drug combinations safely, balancing optimism and caution.

We consider two functions on Sp(g,R) with values in the cyclic group of order four {1,-1,i,-i}. One was defined by Lion and Vergne. The other is -i raised to the power given by an integer valued function defined by Masbaum and the author (initially on the mapping class group of a surface). We identify these functions w…

New algorithm reduces regret in asynchronous multiplayer bandits to constant or logarithmic levels.

In this paper, we consider the generalized lambda constant and the existence of ground states of the generalized Perelman's W-functional from a variational formulation. One result is concerned with the estimation of the generalized $λ$ constant. The other results are about the existence of ground states of generalized …

We show how Lasry-Lions's result on regularization of functions defined on $\mathbb{R}^n$ or on Hilbert spaces by sup-inf convolutions with squares of distances can be extended to (finite or infinite dimensional) Riemannian manifolds $M$ of bounded sectional curvature. More specifically, among other things we show that…

Safe reinforcement learning with logical constraints for optimal policy synthesis.

Calls to arms to build interpretable models express a well-founded discomfort with machine learning. Should a software agent that does not even know what a loan is decide who qualifies for one? Indeed, we ought to be cautious about injecting machine learning (or anything else, for that matter) into applications where t…

The paper examines stability of Sobolev inequalities on manifolds with Ricci curvature bounds.

Lions and Musiela (2007) give sufficient conditions to verify when a stochastic exponential of a continuous local martingale is a martingale or a uniformly integrable martingale. Blei and Engelbert (2009) and Mijatović and Urusov (2012c) give necessary and sufficient conditions in the case of perfect correlation (ρ=1).…

Reinforcement Learning (RL) has demonstrated state-of-the-art results in a number of autonomous system applications, however many of the underlying algorithms rely on black-box predictions. This results in poor explainability of the behaviour of these systems, raising concerns as to their use in safety-critical applica…

Is AdamW effective under heavy-tailed noise?

New optimization method combines gradient clipping and non-Euclidean smoothness.

Mean field game theory studies the behavior of a large number of interacting individuals in a game theoretic setting and has received a lot of attention in the past decade (Lasry and Lions, Japanese journal of mathematics, 2007). In this work, we derive mean field game partial differential equation systems from determi…

We decompose, within an ARCH framework, the daily volatility of stocks into overnight and intra-day contributions. We find, as perhaps expected, that the overnight and intra-day returns behave completely differently. For example, while past intra-day returns affect equally the future intra-day and overnight volatilitie…

Inspired by recent work of P.-L. Lions on conditional optimal control, we introduce a problem of optimal stopping under bounded rationality: the objective is the expected payoff at the time of stopping, conditioned on another event. For instance, an agent may care only about states where she is still alive at the time …

We prove some old and new isoperimetric inequalities with the best constant using the ABP method applied to an appropriate linear Neumann problem. More precisely, we obtain a new family of sharp isoperimetric inequalities with weights (also called densities) in open convex cones of $\mathbb{R}^n$. Our result applies to…

The Prescriptive Canvas improves business outcomes by directly prescribing actions based on predictions.

In the first part of the paper we investigate some geometric features of Moser-Trudinger inequalities on complete non-compact Riemannian manifolds. By exploring rearrangement arguments, isoperimetric estimates, and gluing local uniform estimates via Gromov's covering lemma, we provide a Coulhon, Saloff-Coste and Varopo…

Enhanced ICM ensemble detects concept drift better with novel betting functions.

A method for classifying points with minimal queries using Hermite polynomials.

Deep learning has become increasingly popular in both supervised and unsupervised machine learning thanks to its outstanding empirical performance. However, because of their intrinsic complexity, most deep learning methods are largely treated as black box tools with little interpretability. Even though recent attempts …

Bayesian model selection can be misled by ELBO under certain conditions.

Charmer improves character-level adversarial attacks for language models.

This paper improves SAM by reformulating it as a bilevel optimization problem.

FedLion improves Federated Learning by speeding up convergence and reducing communication costs.

New MCMC method estimates differential privacy from multiple MIAs without worst-case assumptions.

SAMPa speeds up SAM by parallelizing its computations.

Paper proposes COM-QEL to avoid overoptimistic solutions in offline optimization.

Novel approach uses ENN for UQ in gust predictions, reducing RMSE and improving confidence.

Experiment shows author rankings can improve peer review scores.

The appeal of metric evaluation of research impact has attracted considerable interest in recent times. Although the public at large and administrative bodies are much interested in the idea, scientists and other researchers are much more cautious, insisting that metrics are but an auxiliary instrument to the qualitati…