arXiv research

Makeev proved that among centrally symmetric four-dimensional polytopes, with more than twenty facets and circumscribed about the Euclidean ball of diameter one, there is no universal cover for the family of unit diameter sets. In this paper we examine the converse problem, and prove that each centrally symmetric polyt…

Paper proves GDL models can approximate any continuous function on non-Euclidean data.

The study characterizes quasiperiodic surfaces in pseudo-hyperbolic spaces with curvature conditions.

New method makes robust estimators work without knowing corruption levels.

Signatures of universality are detected by comparing individual eigenvalue distributions and level spacings from financial covariance matrices to random matrix predictions. A chopping procedure is devised in order to produce a statistical ensemble of asset-price covariances from a single instance of financial data sets…

We prove that there exists a universal constant $c$ such that any closed hyperbolic 3-manifold admits a triangulation of treewidth at most $c$ times its volume. The converse is not true: we show there exists a sequence of hyperbolic 3-manifolds of bounded treewidth but volume approaching infinity. Along the way, we pro…

Consider unsupervised clustering of objects drawn from a discrete set, through the use of human intelligence available in crowdsourcing platforms. This paper defines and studies the problem of universal clustering using responses of crowd workers, without knowledge of worker reliability or task difficulty. We model sto…

Much of the focus in the design of deep neural networks has been on improving accuracy, leading to more powerful yet highly complex network architectures that are difficult to deploy in practical scenarios, particularly on edge devices such as mobile and other consumer devices given their high computational and memory …

New proof shows incremental flow models are essential for universal generation.

Study confirms the square-root law in price impact across Tokyo stocks.

Let $M$ be complete nonpositively curved Riemannian manifold of finite volume whose fundamental group $Γ$ does not contain a finite index subgroup which is a product of infinite groups. We show that the universal cover $\tilde M$ is a higher rank symmetric space iff $H^2_b(M;\R)\to H^2(M;\R)$ is injective (and otherwis…

This is the second part of the works on Hausdorff dimensions of Schottky groups. It has been conjectured that the Hausdorff dimensions of nonclassical Schottky groups are strictly bounded from below. In this second part of our works we provide a resolution of this conjecture, we prove that there exists a universal posi…

Banach's fixed point theorem for contraction maps has been widely used to analyze the convergence of iterative methods in non-convex problems. It is a common experience, however, that iterative maps fail to be globally contracting under the natural metric in their domain, making the applicability of Banach's theorem li…

Study examines cash conversion cycle in manufacturing firms, finding negative relationships with profitability and size.

Framework converts singer identity and vocal technique from non-parallel corpora.

FasterVoiceGrad speeds up VC by 6-7x with novel distillation.

Automated system extracts medication regimens from medical conversations.

Conversion prediction plays an important role in online advertising since Cost-Per-Action (CPA) has become one of the primary campaign performance objectives in the industry. Unlike click prediction, conversions have different types in nature, and each type may be associated with different decisive factors. In this pap…

UQE uses LLMs to analyze unstructured data efficiently.

FedConPE improves conversational recommender systems efficiency and privacy.

We present an approach towards convex optimization that relies on a novel scheme which converts online adaptive algorithms into offline methods. In the offline optimization setting, our derived methods are shown to obtain favourable adaptive guarantees which depend on the harmonic sum of the queried gradients. We furth…

Contextual bandit algorithms provide principled online learning solutions to balance the exploitation-exploration trade-off in various applications such as recommender systems. However, the learning speed of the traditional contextual bandit algorithms is often slow due to the need for extensive exploration. This poses…

Study proposes a time-aware model to predict user conversion intent.

The goal of online display advertising is to entice users to "convert" (i.e., take a pre-defined action such as making a purchase) after clicking on the ad. An important measure of the value of an ad is the probability of conversion. The focus of this paper is the development of a computationally efficient, accurate, a…

USS fund risk assessment shows low default chance but high overfunding.

CycleGAN-VC3 improves CycleGAN-VCs for mel-spectrogram conversion.

A new algorithm for conversational recommendation systems using dueling bandits in GLMs.

The paper extracts structured data from physician-patient conversations, reducing clerical burden.

Schedule-free SGD is optimal for nonconvex optimization problems.

Improved autoencoder for F0-consistent voice conversion.

Improved conversion rate prediction in online advertising using self-supervised pre-training.

A fast voice conversion method using diffusion models.

A method corrects feedback shift in predicting conversion rates with delayed feedback.

Proposes a new voice conversion model that preserves pitch patterns.

We present a voice conversion solution using recurrent sequence to sequence modeling for DNNs. Our solution takes advantage of recent advances in attention based modeling in the fields of Neural Machine Translation (NMT), Text-to-Speech (TTS) and Automatic Speech Recognition (ASR). The problem consists of converting be…

The paper provides a converse to linking theorems for graphs in 3-space and higher dimensions.

This paper proposes a voice conversion (VC) method using sequence-to-sequence (seq2seq or S2S) learning, which flexibly converts not only the voice characteristics but also the pitch contour and duration of input speech. The proposed method, called ConvS2S-VC, has three key features. First, it uses a model with a fully…

A theorem transforms Lorentzian to signature-changing metrics.

Let $(W,S)$ be a Coxeter system with Davis complex $Σ$. The polyhedral automorphism group $G$ of $Σ$ is a locally compact group under the compact-open topology. If $G$ is a discrete group (as characterised by Haglund--Paulin), then the set $\mathcal V_u(G)$ of uniform lattices in $G$ is discrete. Whether the converse i…

We address the problem of speech act recognition (SAR) in asynchronous conversations (forums, emails). Unlike synchronous conversations (e.g., meetings, phone), asynchronous domains lack large labeled datasets to train an effective SAR model. In this paper, we propose methods to effectively leverage abundant unlabeled …

This paper explores how LLMs can improve pipeline-based conversational agents.

A new framework converts EEG signals between subjects and tasks.

Unified approach for conversational recommendation by integrating attributes and items.

Neuro-symbolic system tackles conversational AI's need for natural, broad-ranging dialogue.

Estimates conversion probabilities from click sequences with privacy constraints.

Study finds neural dialog models struggle with conversational tasks.

Deep learning improves conversational recommender systems.

In this work we explored building automatic speech recognition models for transcribing doctor patient conversation. We collected a large scale dataset of clinical conversations ($14,000$ hr), designed the task to represent the real word scenario, and explored several alignment approaches to iteratively improve data qua…