arXiv research

Breathing k-means outperforms greedy k-means++ in clustering.

In reinforcement learning the Q-values summarize the expected future rewards that the agent will attain. However, they cannot capture the epistemic uncertainty about those rewards. In this work we derive a new Bellman operator with associated fixed point we call the `knowledge values'. These K-values compress both the …

We show that the Rademacher complexity of any $\mathbb{R}^{K}$-valued function class composed with an $\ell_{\infty}$-Lipschitz function is bounded by the maximum Rademacher complexity of the restriction of the function class along each coordinate, times a factor of $\tilde{O}(\sqrt{K})$.

The abstract discusses embedding theorems for pseudo-Kähler manifolds.

K-Nearest neighbor classifier (k-NNC) is simple to use and has little design time like finding k values in k-nearest neighbor classifier, hence these are suitable to work with dynamically varying data-sets. There exists some fundamental improvements over the basic k-NNC, like weighted k-nearest neighbors classifier (wh…

Analytic submanifolds of cocycles reveal discrete cohomology spaces.

New research shows Manturov-Nikonov map fails for large k values.

DeepDPM clusters images without knowing the number of clusters.

The paper compares one-hot encoding to Naïve Bayes for categorical variables.

High frequency based estimation methods for a semiparametric pure-jump subordinated Brownian motion exposed to a small additive microstructure noise are developed building on the two-scales realized variations approach originally developed by Zhang et. al. (2005) for the estimation of the integrated variance of a conti…

In this paper, we propose a model-based clustering method (TVClust) that robustly incorporates noisy side information as soft-constraints and aims to seek a consensus between side information and the observed data. Our method is based on a nonparametric Bayesian hierarchical model that combines the probabilistic model …

Eigen-stratified models reduce model size and improve performance.

Study develops and improves risk models using machine learning methods.

Algorithms compute length spectra of torus graphs efficiently.

New algorithm maximizes non-monotone adaptive submodular functions in linear time.

SPO optimizes LLMs by eliminating group-based baselines and variance issues.

Paper develops an efficient mean estimator for 1-bit communication constraints.

Optimizes reinforcement learning by prioritizing sets of samples over individual ones.

The paper analyzes how repeating epochs affects data scaling in linear regression.

Paper shows leafwise cohomological expression for dynamical zeta functions.

Study on 2-valued dynamics on complex plane, showing some dynamics can't be group actions.

The paper studies dynamic star-shaped risk measures and their representation.

Study circles to understand dynamics and rigidity in homogeneous spaces.

Paper connects dynamics of mechanical systems to Reeb dynamics.

Two heuristics solve dynamic multiple travelling salesmen problems.

In this paper we present a theoretical framework for studying coherent acceptability indices in a dynamic setup. We study dynamic coherent acceptability indices and dynamic coherent risk measures, and we establish a duality between them. We derive a representation theorem for dynamic coherent risk measures in terms of …

DOODL learns shared spectral dynamics across related dynamical systems.

We propose a new class of mappings, called Dynamic Limit Growth Indices, that are designed to measure the long-run performance of a financial portfolio in discrete time setup. We study various important properties for this new class of measures, and in particular, we provide necessary and sufficient condition for a Dyn…

SPICE estimates sparse linear dynamic networks without hyperparameters.

In this paper we present a theoretical framework for determining dynamic ask and bid prices of derivatives using the theory of dynamic coherent acceptability indices in discrete time. We prove a version of the First Fundamental Theorem of Asset Pricing using the dynamic coherent risk measures. We introduce the dynamic …

Dynamical-VAE learns causal dynamics from POMDPs using future information.

Most real world phenomena such as sunlight distribution under a forest canopy, minerals concentration, stock valuation, exhibit nonstationary dynamics i.e. phenomenon variation changes depending on the locality. Nonstationary dynamics pose both theoretical and practical challenges to statistical machine learning algori…

Unified analysis of DLNs using DMFT reveals dynamics of loss convergence and generalization trade-offs.

Method learns to map dynamics of different systems.

dLDS models neural dynamics as sparse combinations of simpler components.

Reinforcement learning would enjoy better success on real-world problems if domain knowledge could be imparted to the algorithm by the modelers. Most problems have both hidden state and unknown dynamics. Partially observable Markov decision processes (POMDPs) allow for the modeling of both. Unfortunately, they do not p…

We consider trivializations of second iterated bundles of a Lie group that preserve lifted group structures. With such a trivialization, we elaborate Hamiltonian dynamics on cotangent, Lagrangian dynamics on tangent bundles and, both Hamiltonian and Lagrangian dynamics on Tulczyjew's symplectic space which is tangent o…

Framework for quantifying uncertainty in dynamic processes.

This survey clarifies dynamic network terminology and reviews GNN models for dynamic networks.

Framework infers Langevin dynamics from stochastic observations of latent systems.

The paper introduces a dynamic MVP model using high-frequency financial data.

The paper extends Vlasov kinetic theory to time-dependent dynamics using cosymplectic and cocontact manifolds.

NDS learns dynamical models with prior knowledge, improving accuracy and efficiency.

New method learns population dynamics from snapshots, outperforming existing models.

Paper uses Chebyshev Tensors for accurate dynamic sensitivities and ISDA SIMM computation.

Model dynamic customer sensitivities across categories.

Survey on computational models in dynamical systems, including new universality concepts.

FNSDA adapts to new dynamics via Fourier space adaptation.