arXiv research

The paper identifies saddlepoints in unsupervised auto-encoding neural nets.

Study improves BN TTA under distribution shift using higher-order asymptotics.

We discuss the use of saddlepoint methods in the analysis of portfolios, with particular reference to credit portfolios. The objective is to proceed from a model of the loss distribution, given through probabilities, correlations and the like, to an analytical approximation of the distribution. Once this is done we sho…

Proposes a new sampling policy for ranking and selection problems.

The Lugannani-Rice formula is a saddlepoint approximation method for estimating the tail probability distribution function, which was originally studied for the sum of independent identically distributed random variables. Because of its tractability, the formula is now widely used in practical financial engineering as …

In this paper we prove an approximate formula expressed in terms of elementary functions for the implied volatility in the Heston model. The formula consists of the constant and first order terms in the large maturity expansion of the implied volatility function. The proof is based on saddlepoint methods and classical …

We propose a new Quantization algorithm for the approximation of inhomogeneous random walks, which are the key terms for the valuation of CDO-tranches in latent factor models. This approach is based on a dual quantization operator which posses an intrinsic stationarity and therefore automatically leads to a second orde…

Deep generative models can learn to generate realistic-looking images, but many of the most effective methods are adversarial and involve a saddlepoint optimization, which requires a careful balancing of training between a generator network and a critic network. Maximum mean discrepancy networks (MMD-nets) avoid this i…

Annealed Entropic Allocation improves ranking and selection by mitigating hard switching and improving finite-budget discrimination.

Determinantal Point Processes (DPPs) are popular models for point processes with repulsion. They appear in numerous contexts, from physics to graph theory, and display appealing theoretical properties. On the more practical side of things, since DPPs tend to select sets of points that are some distance apart (repulsion…

Quantum field theory connects deep neural networks to criticality.

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

Geometric Gaussian approximations capture any distribution.

Method approximates Riemannian barycenter on manifolds.

We consider in this paper the optimal approximations of convex univariate functions with feed-forward Relu neural networks. We are interested in the following question: what is the minimal approximation error given the number of approximating linear pieces? We establish the necessary and sufficient conditions and uniqu…

Efficiently reduces tensor ranks using mean-field approximation.

Study approximates unknown function levels with queries.

We study sparse approximate solutions to convex optimization problems. It is known that in many engineering applications researchers are interested in an approximate solution of an optimization problem as a linear combination of elements from a given system of elements. There is an increasing interest in building such …

Softmax attention approximates complex functions and subsumes many known universal approximators.

Improved matrix approximation using randomized algorithms.

Deviation inequalities for stochastic approximation methods.

Neural approximate computing gains enormous energy-efficiency at the cost of tolerable quality-loss. A neural approximator can map the input data to output while a classifier determines whether the input data are safe to approximate with quality guarantee. However, existing works cannot maximize the invocation of the a…

Approximate symmetries of geodesic equations on 2-spheres are studied. These are the symmetries of the perturbed geodesic equations which represent approximate path of a particle rather than exact path. After giving the exact symmetries of the geodesic equations, two different approaches to study the approximate symmet…

We are concerned with an approximation problem for a symmetric positive semidefinite matrix due to motivation from a class of nonlinear machine learning methods. We discuss an approximation approach that we call {matrix ridge approximation}. In particular, we define the matrix ridge approximation as an incomplete matri…

Transformers use ReLUs to approximate softmax efficiently.

Approximating complex curves with simple parametric curves is widely used in CAGD, CG, and CNC. This paper presents an algorithm to compute a certified approximation to a given parametric space curve with cubic B-spline curves. By certified, we mean that the approximation can approximate the given curve to any given pr…

Recently, variational approximations such as the mean field approximation have received much interest. We extend the standard mean field method by using an approximating distribution that factorises into cluster potentials. This includes undirected graphs, directed acyclic graphs and junction trees. We derive generaliz…

Adaptive approximations improve variational inference for complex models.

Non-negative $L_1$-approximating polynomials for Gaussian distributions are proven for certain classes of sets.

Paper introduces new approximations for lognormal sums, matching comonotonicity and moments.

Paper analyzes normal approximation for two-timescale stochastic algorithms, revealing interaction between fast and slow timescales.

One-pass algorithm finds small subset for $\ell_p$ subspace approximation with additive error.

We are interested in approximation of a multivariate function $f(x_1,\dots,x_d)$ by linear combinations of products $u^1(x_1)\cdots u^d(x_d)$ of univariate functions $u^i(x_i)$, $i=1,\dots,d$. In the case $d=2$ it is a classical problem of bilinear approximation. In the case of approximation in the $L_2$ space the bili…

A new method for efficient Gaussian process inference using sparse approximations.

In this paper, we propose a low-rank approximation method based on discrete least-squares for the approximation of a multivariate function from random, noisy-free observations. Sparsity inducing regularization techniques are used within classical algorithms for low-rank approximation in order to exploit the possible sp…

Neural network based approximate computing is a universal architecture promising to gain tremendous energy-efficiency for many error resilient applications. To guarantee the approximation quality, existing works deploy two neural networks (NNs), e.g., an approximator and a predictor. The approximator provides the appro…

The paper approximates supply curves using a one-step basis method.

The paper defines a new concept of approximability for Lagrangian submanifolds.

Boosting Nyström improves accuracy of matrix approximations.

High-probability bound for distributed stochastic approximation tracking error.

Nyström KPCA balances computational efficiency and statistical accuracy.

Improves Laplace approximation for Bayesian inference on Riemannian manifolds.

We approximate derivatives of functions on manifolds by embedding them and applying vector-valued operators.

We discuss Bayesian methods for learning Bayesian networks when data sets are incomplete. In particular, we examine asymptotic approximations for the marginal likelihood of incomplete data given a Bayesian network. We consider the Laplace approximation and the less accurate but more efficient BIC/MDL approximation. We …

Proposes efficient Gaussian approximations for non-Gaussian likelihoods.

Gradient descent trains shallow neural networks to approximate functions in 1D.

Method uses DNNs to approximate functions with specific asymptotic behavior.

We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for universal approximation using continuous-time deep residual networks, which can …