A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Study on charged parallel spinors and mass-charge inequalities.
Optimized parallel RNN training reaches up to 845x speedup.
We design and analyse variations of the classical Thompson sampling (TS) procedure for Bayesian optimisation (BO) in settings where function evaluations are expensive, but can be performed in parallel. Our theoretical analysis shows that a direct application of the sequential Thompson sampling algorithm in either synch…
Non-negative Matrix Factorization (NMF) is a key kernel for unsupervised dimension reduction used in a wide range of applications, including topic modeling, recommender systems and bioinformatics. Due to the compute-intensive nature of applications that must perform repeated NMF, several parallel implementations have b…
Curvature criteria for A-simple singularities and their parallel curves identified.
Stochastic gradient descent~(SGD) and its variants have become more and more popular in machine learning due to their efficiency and effectiveness. To handle large-scale problems, researchers have recently proposed several parallel SGD methods for multicore systems. However, existing parallel SGD methods cannot achieve…
End-to-end DA method for domain-invariant CNNs using parallel audio recordings.
This paper improves parallel belief propagation for scalable machine learning.
PHS optimizes hyperparameters in parallel for expensive computations.
Improved voice conversion with semi-supervised learning.
Linear algebra approach for parallel deep learning models.
We prove that the length difference between a closed periodic curve and its parallel curve at a sufficiently small distance is proportional to the rotation index. As an application, the rotation index of a curve could be estimated by means of Cauchy-Crofton formula.
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neural network based approach to extract parallel sentences from collections of multilingual texts. Our experiments with noisy parallel corpora…
Motivated by the study of Weyl structures on conformal manifolds admitting parallel weightless forms, we define the notion of conformal product of conformal structures and study its basic properties. We obtain a classification of Weyl manifolds carrying parallel forms, and we use it to investigate the holonomy of the a…
We establish variational formulas for Ricci upper and lower bounds, as well as a derivative formula for the Ricci curvature. As applications, constant curvature manifolds, Einstein manifolds and Ricci parallel manifolds are identified, respectively, with different integral-differential formulas and semigroup inequaliti…
Parallel sentences are a relatively scarce but extremely useful resource for many applications including cross-lingual retrieval and statistical machine translation. This research explores our methodology for mining such data from previously obtained comparable corpora. The task is highly practical since non-parallel m…
Parallelized bandit algorithms speed up decision-making.
Decomposes submanifolds with special tensors into simpler parts.
The book contents: the notion of Myller configurations, Darboux frame, fundamental formulae and fundamental theorem of existence. The complete system of invariants allows to introduce the notions of Myller parallelism and concurrence as well as a famous Klein's formula. By way it is obtained an important generalization…
Method predicts how probability distributions evolve over time.
Proposes a new PBO method with theoretical guarantees.
This paper optimizes object tracking on edge devices with small matrices.
This paper uses supervised learning to predict optimal chunk-size for parallel linear algebra operations.
Absolute parallelism geometry is frequently used for physical applications. It has two main defects, from the point of view of applications. The first is the identical vanishing of its curvature tensor. The second is that its autoparallel paths do not represent physical trajectories. The present work shows how these de…
Parallel sampling for smooth distributions with fast convergence.
In many applications of black-box optimization, one can evaluate multiple points simultaneously, e.g. when evaluating the performances of several different neural network architectures in a parallel computing environment. In this paper, we develop a novel batch Bayesian optimization algorithm --- the parallel knowledge…
Parallel sentences are a relatively scarce but extremely useful resource for many applications including cross-lingual retrieval and statistical machine translation. This research explores our new methodologies for mining such data from previously obtained comparable corpora. The task is highly practical since non-para…
We give criteria for which a principal curvature becomes a bounded -function at non-degenerate singular points of wave fronts by using geometric invariants. As applications, we study singularities of parallel surfaces and extended distance squared functions of wave fronts. Moreover, we relate these singularit…
Study torsion parallel spinors on Lorentzian 4-manifolds and their evolution flows.
The paper explores Lorentzian connections with parallel skew torsion.
We propose a flexible framework for spectral conversion (SC) that facilitates training with unaligned corpora. Many SC frameworks require parallel corpora, phonetic alignments, or explicit frame-wise correspondence for learning conversion functions or for synthesizing a target spectrum with the aid of alignments. Howev…
A new method combines MCMC results to avoid failures in parallel computing.
We develop a parallel variational inference (VI) procedure for use in data-distributed settings, where each machine only has access to a subset of data and runs VI independently, without communicating with other machines. This type of "embarrassingly parallel" procedure has recently been developed for MCMC inference al…
In real world industrial applications of topic modeling, the ability to capture gigantic conceptual space by learning an ultra-high dimensional topical representation, i.e., the so-called "big model", is becoming the next desideratum after enthusiasms on "big data", especially for fine-grained downstream tasks such as …
We introduce a novel approach for parallelizing MCMC inference in models with spatially determined conditional independence relationships, for which existing techniques exploiting graphical model structure are not applicable. Our approach is motivated by a model of seismic events and signals, where events detected in d…
New method solves blind inverse problems by optimizing both operator and image parameters.
I prove the bistability of linear evolution equations in a Banach space , where the operator-valued function is of the form for a binary operator-valued function and a scalar function . The constant that bounds the solutions of the equation is computed explicitly; it i…
OptEx accelerates first-order optimization with parallelized iterations.
New submersions found in nearly Kähler geometry.
We study special almost Kaehler manifolds whose curvature tensor satisfies the second curvature condition of Gray. It is shown that for such manifolds, the torsion of the first canonical Hermitian is parallel. This enables us to show that every AK_2-manifold has parallel torsion. Some applications of this result, conce…
Can one parallelize complex exploration exploitation tradeoffs? As an example, consider the problem of optimal high-throughput experimental design, where we wish to sequentially design batches of experiments in order to simultaneously learn a surrogate function mapping stimulus to response and identify the maximum of t…
The numerical solution of large-scale PDEs, such as those occurring in data-driven applications, unavoidably require powerful parallel computers and tailored parallel algorithms to make the best possible use of them. In fact, considerations about the parallelization and scalability of realistic problems are often criti…
Many applications in Bayesian statistics are extremely computationally intensive. However, they are often inherently parallel, making them prime targets for modern massively parallel processors. Multi-core and distributed computing is widely applied in the Bayesian community, however, very little attention has been giv…
Ouroboros accelerates training of large Transformer models.
Study classifies 3D Einstein manifolds with cyclic Ricci tensor.
Clustering samples according to an effective metric and/or vector space representation is a challenging unsupervised learning task with a wide spectrum of applications. Among several clustering algorithms, k-means and its kernelized version have still a wide audience because of their conceptual simplicity and efficacy.…
The past years have witnessed many dedicated open-source projects that built and maintain implementations of Support Vector Machines (SVM), parallelized for GPU, multi-core CPUs and distributed systems. Up to this point, no comparable effort has been made to parallelize the Elastic Net, despite its popularity in many h…
Batch-splitting (data-parallelism) is the dominant distributed Deep Neural Network (DNN) training strategy, due to its universal applicability and its amenability to Single-Program-Multiple-Data (SPMD) programming. However, batch-splitting suffers from problems including the inability to train very large models (due to…