arXiv research

The paper provides Gaussian approximations for decentralized Federated Learning.

In this paper we derive an easily computed approximation to European basket call prices for a local volatility jump-diffusion model. We apply the asymptotic expansion method to find the approximate value of the lower bound of European basket call prices. If the local volatility function is time independent then there i…

The study provides conditions for approximating Riemannian manifolds with polyhedral metrics.

Unified view of federated learning and distributed RL using local stochastic approximation.

Let $Y\subset{\mathbb R}^n$ be a triangulable set and let $r$ be either a positive integer or $r=\infty$. We say that $Y$ is a $\mathscr{C}^r$-approximation target space, or a $\mathscr{C}^r\text{-}\mathtt{ats}$ for short, if it has the following universal approximation property: For each $m\in{\mathbb N}$ and each loc…

The study explores various localized bases and their duals for scattered data approximation.

Study analyzes error in ReLU networks with local connections.

New method improves Euler approximation for local stochastic volatility models.

A new TwinGP framework for efficient large-scale GP modeling.

Matrix approximation is a common tool in machine learning for building accurate prediction models for recommendation systems, text mining, and computer vision. A prevalent assumption in constructing matrix approximations is that the partially observed matrix is of low-rank. We propose a new matrix approximation model w…

Study approximates unknown function levels with queries.

We propose a new localized inference algorithm for answering marginalization queries in large graphical models with the correlation decay property. Given a query variable and a large graphical model, we define a much smaller model in a local region around the query variable in the target model so that the marginal dist…

New method controls error in low-dimensional marginals of spatial models.

Paper provides an explicit formula for local volatility in Cheyette models.

L-C2ST improves local diagnostics for SBI approximations.

We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which scales linearly in the underlying dimension and the number of training examples. The time complexity of our algorithm to find an approximate local minimum is even faster than that of gradie…

Classifiers label data as belonging to one of a set of groups based on input features. It is challenging to obtain accurate classification performance when the feature distributions in the different classes are complex, with nonlinear, overlapping and intersecting supports. This is particularly true when training data …

Paper develops Gaussian approximations and bootstrap for federated LSA with trade-off bounds.

Local network community detection aims to find a single community in a large network, while inspecting only a small part of that network around a given seed node. This is much cheaper than finding all communities in a network. Most methods for local community detection are formulated as ad-hoc optimization problems. In…

Boosting Variational Inference improves posterior approximations with adaptive step-sizes.

Develops a new theory for approximating functions on massive data.

Paper presents a simple method for accurate user localization in urban areas.

Paper studies Transformer learning theory for Euclidean and Riemannian domains.

Optimizers find approximate global minima in non-convex problems.

New method for CMS derivatives pricing using Watanabe's expansions.

We prove that for a compact subgroup $H$ of a locally compact Hausdorff group $G$, the following properties are mutually equivalent: (1) $G/H$ is a manifold, (2) $G/H$ is finite-dimensional and locally connected, (3) $G/H$ is locally contractible, (4) $G/H$ is an ANE for paracompact spaces, (5) $G/H$ is a metrizable $G…

Expectation propagation (EP) is a deterministic approximation algorithm that is often used to perform approximate Bayesian parameter learning. EP approximates the full intractable posterior distribution through a set of local approximations that are iteratively refined for each datapoint. EP can offer analytic and comp…

Efficient local planning with linear approximations for agents with limited simulator access.

In this work, we provide theoretical guarantees for reward decomposition in deterministic MDPs. Reward decomposition is a special case of Hierarchical Reinforcement Learning, that allows one to learn many policies in parallel and combine them into a composite solution. Our approach builds on mapping this problem into a…

Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This paper highlights the importance of defining the right locality, the neighborhood on which a local su…

Paper approximates rough stochastic local volatility models for efficient computation.

Given a graphical model (GM), computing its partition function is the most essential inference task, but it is computationally intractable in general. To address the issue, iterative approximation algorithms exploring certain local structure/consistency of GM have been investigated as popular choices in practice. Howev…

A new method automatically and dynamically sets learning rates in deep learning.

The paper connects machine learning interpretability with learning theory.

Locally approximating groups of homeomorphisms reveal manifold properties.

Paper proposes a new method for WDRO with local perturbations, achieving better accuracy.

Recently, some works have suggested methods to combine variational probabilistic inference with Monte Carlo sampling. One promising approach is via local optimal transport. In this approach, a gradient steepest descent method based on local optimal transport principles is formulated to transform deterministically point…

This paper introduces a new method for semi-supervised learning on high dimensional nonlinear manifolds, which includes a phase of unsupervised basis learning and a phase of supervised function learning. The learned bases provide a set of anchor points to form a local coordinate system, such that each data point $x$ on…

We consider random walks on locally compact groups, extending the geometric criteria for the identification of their Poisson boundary previously known for discrete groups. First, we prove a version of the Shannon-McMillan-Breiman theorem, which we then use to generalize Kaimanovich's ray approximation and strip approxi…

Stochastic gradient descent optimizes Nyström samples for kernel matrix approximation.

Gradients help find global optima in complex functions.

Improved API to achieve optimal error bound and query complexity in local planning.

We design a stochastic algorithm to train any smooth neural network to $\varepsilon$-approximate local minima, using $O(\varepsilon^{-3.25})$ backpropagations. The best result was essentially $O(\varepsilon^{-4})$ by SGD. More broadly, it finds $\varepsilon$-approximate local minima of any smooth nonconvex function in …

Local GP approach improves simulation efficiency for large datasets.

This paper discusses the short-maturity behavior of Asian option prices and hedging portfolios. We consider the risk-neutral valuation and the delta value of the Asian option having a Hölder continuous payoff function in a local volatility model. The main idea of this analysis is that the local volatility model can be …

In this paper we aim for a generalisation of the Steenrod Approximation Theorem from, concerning a smoothing procedure for sections in smooth locally trivial bundles. The generalisation is that we consider locally trivial smooth bundles with a possibly infinite-dimensional typical fibre. The main result states that a c…

Folded concave penalization methods have been shown to enjoy the strong oracle property for high-dimensional sparse estimation. However, a folded concave penalization problem usually has multiple local solutions and the oracle property is established only for one of the unknown local solutions. A challenging fundamenta…

Paper explores supervised learning methods to approximate ideal observer for joint signal detection and localization.