arXiv research

New recursion formula for non-orientable surfaces resolves divergences.

Two new inverse-free ELM algorithms for incremental and decremental learning are proposed.

In this paper, we develop an approach to recursively estimate the quadratic risk for matrix recovery problems regularized with spectral functions. Toward this end, in the spirit of the SURE theory, a key step is to compute the (weak) derivative and divergence of a solution with respect to the observations. As such a so…

We introduce a recursive adaptive group lasso algorithm for real-time penalized least squares prediction that produces a time sequence of optimal sparse predictor coefficient vectors. At each time index the proposed algorithm computes an exact update of the optimal $\ell_{1,\infty}$-penalized recursive least squares (R…

Stochastic Variance-Reduced Cubic regularization (SVRC) algorithms have received increasing attention due to its improved gradient/Hessian complexities (i.e., number of queries to stochastic gradient/Hessian oracles) to find local minima for nonconvex finite-sum optimization. However, it is unclear whether existing SVR…

The inverse-free extreme learning machine (ELM) algorithm proposed in [4] was based on an inverse-free algorithm to compute the regularized pseudo-inverse, which was deduced from an inverse-free recursive algorithm to update the inverse of a Hermitian matrix. Before that recursive algorithm was applied in [4], its impr…

The paper analyzes SGD with dropout regularization in linear models, proving asymptotic properties and providing inference tools.

A new algorithm, Regular Tree Search, tackles non-convex simulation optimization problems.

We use symplectic cobordism, and the localization result of Ginzburg, Guillemin, and Karshon, to find a wall-crossing formula for the signature of regular symplectic quotients of Hamiltonian torus actions. The formula is recursive, depending ultimately on fixed point data. In the case of a circle action, we obtain a fo…

Study on private algorithms for saddle point and variational inequalities, improving efficiency and applicability.

We study recursive-cube-of-rings (RCR), a class of scalable graphs that can potentially provide rich inter-connection network topology for the emerging distributed and parallel computing infrastructure. Through rigorous proof and validating examples, we have corrected previous misunderstandings on the topological prope…

We revisit the development of grid based recursive approximate filtering of general Markov processes in discrete time, partially observed in conditionally Gaussian noise. The grid based filters considered rely on two types of state quantization: The \textit{Markovian} type and the \textit{marginal} type. We propose a s…

Recursive neural networks have widely been used by researchers to handle applications with recursively or hierarchically structured data. However, embedded control flow deep learning frameworks such as TensorFlow, Theano, Caffe2, and MXNet fail to efficiently represent and execute such neural networks, due to lack of s…

We give the first algorithm for kernel Nyström approximation that runs in *linear time in the number of training points* and is provably accurate for all kernel matrices, without dependence on regularity or incoherence conditions. The algorithm projects the kernel onto a set of $s$ landmark points sampled by their *rid…

Paper defines Farey Recursive Functions and explores their properties.

The paper explores generalizations of Mirzakhani's recursion and computes volumes for physical gravity models.

We review properties of so-called special conformal Killing tensors on a Riemannian manifold $(Q,g)$ and the way they give rise to a Poisson-Nijenhuis structure on the tangent bundle $TQ$. We then address the question of generalizing this concept to a Finsler space, where the metric tensor field comes from a regular La…

RocketStack integrates predictions from multiple base learners using a recursive stacking architecture up to ten levels.

Gradient descent with chaotic perturbations improves generalization.

Tab-TRM uses recursive model for insurance pricing on tabular data.

Harer and Zagier proved a recursion to enumerate gluings of a $2d$-gon that result in an orientable genus $g$ surface, in their work on Euler characteristics of moduli spaces of curves. Analogous results have been discovered for other enumerative problems, so it is natural to pose the following question: how large is t…

We consider here a generalization of a well known discrete dynamical system produced by the bisection of reflection angles that are constructed recursively between two lines in the Euclidean plane. It is shown that similar properties of such systems are observed when the plane is replaced by a regular surface in ${\mat…

This paper studies recursive ensembles driven by Fibonacci updates, improving learning dynamics.

The article improves prediction by aggregating Kalman recursions online.

Solves a recursion for Gromov-Witten invariants of the unknot.

New methods optimize personalized treatment assignment in trials with many arms.

New recursion found for hyperbolic sphere volumes.

We formalize the notion of a pseudo-ensemble, a (possibly infinite) collection of child models spawned from a parent model by perturbing it according to some noise process. E.g., dropout (Hinton et. al, 2012) in a deep neural network trains a pseudo-ensemble of child subnetworks generated by randomly masking nodes in t…

This work generalizes a formula linking Seiberg-Witten prepotential and topological recursion.

LASER compresses recursive model activations by exploiting their low-dimensional structure.

We describe a method for recursively calculating Gromov-Witten invariants of all blowups of the projective plane. This recursive formula is different from the recursive formulas due to Göttsche and Pandharipande in the zero genus case, and Caporaso and Harris in the case of no blowups. We use tropical curves and a recu…

Topological recursion recovers a specific partition function for colored knots.

We derive the Do and Norbury recursion formula for the one-loop mean of an irregular spectral curve from a variant of replica method by Brezín and Hikami. We express this recursion in special times in which all terms $W_1^{(g)}$ of the genus expansion of the one-loop mean are polynomials. We find a generalization of th…

This paper concerns the recursive utility maximization problem under partial information. We first transform our problem under partial information into the one under full information. When the generator of the recursive utility is concave, we adopt the variational formulation of the recursive utility which leads to a s…

A new feature selection method using random forest and Kolmogorov filter.

We study the problem of learning a latent tree graphical model where samples are available only from a subset of variables. We propose two consistent and computationally efficient algorithms for learning minimal latent trees, that is, trees without any redundant hidden nodes. Unlike many existing methods, the observed …

We derive a recursion relation for hyperbolic string vertices and apply it to string field theory.

Benchmarking recursive collapse claims with a new framework under false-positive control.

SRRM improves recursive transport surrogates in the small-discrepancy regime.

The paper analyzes the convergence rates of Q-learning with entropy regularization and linear function approximation.

ERM uses energy-based selection to improve recursive reasoning.

This paper refines the Gaussian Sinkhorn algorithm for general multivariate models.

Study uses reinforcement learning to optimize portfolios under recursive utility.

The paper studies risk-sensitive MDPs with recursive risk measures.

New recursive relation found for a specific torus knot.

We propose a general theory for constructing functorial assignments $Σ\longmapsto Ω_Σ \in E(Σ)$ for a large class of functors $E$ from a certain category of bordered surfaces to a suitable target category of topological vector spaces. The construction proceeds by successive excisions of homotopy classes of embedded pai…

Recursive training of generative models can lead to model collapse, and the recursion converges to a unique limiting distribution.

Paper presents novel online MTL methods using WRLS and OSLSSVR.