Active learning reduces SP calculations by 90%.
problem Efficiently calculating saddle points in energy functions.
method Active learning framework with GPR and GAD.
result Significant reduction in the number of expensive evaluations.
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Gentle Accent Dynamics”
GE2E-AC improves accent classification by focusing on accent embeddings.
problem Training models to predict accent type can lead to learning irrelevant features.
method GE2E-AC trains models to extract accent embeddings, making them closer for the same accent class.
result GE2E-AC outperforms baseline models trained with conventional loss.
This paper describes the data collection effort that is part of the project Sprekend Nederland (The Netherlands Talking), and discusses its potential use in Automatic Accent Location. We define Automatic Accent Location as the task to describe the accent of a speaker in terms of the location of the speaker and its hist…
MPSA-DenseNet improves accent classification accuracy.
problem Accurate English accent identification.
method Combines multi-task learning and PSA attention mechanism with DenseNet.
result MPSA-DenseNet outperforms other models in accent classification.
State-of-the-art automatic speech recognition (ASR) systems struggle with the lack of data for rare accents. For sufficiently large datasets, neural engines tend to outshine statistical models in most natural language processing problems. However, a speech accent remains a challenge for both approaches. Phonologists ma…
Quantum states can be learned efficiently using gentle measurements.
problem Efficiently learning quantum states with minimal measurements.
method Introducing α-LGM measurements and proving strong quantum DPI.
result The number of states needed for accurate learning is of order 1/(ε^2 α^2).
End-to-end speech synthesis is a promising approach that directly converts raw text to speech. Although it was shown that Tacotron2 outperforms classical pipeline systems with regards to naturalness in English, its applicability to other languages is still unknown. Japanese could be one of the most difficult languages …
Mutation graph of support τ-tilting modules over skew-gentle algebras is connected.
problem Understanding the structure of support τ-tilting modules over skew-gentle algebras.
method Introducing mutation of maximal rigid objects and using exchange triangles to define mutations of support τ-tilting modules.
result The mutation graph of support τ-tilting modules over a skew-gentle algebra is connected.
We describe some of the algebra underlying the decomposition of planar grid diagrams. This provides a useful toy model for an extension of Heegaard Floer homology to 3-manifolds with parametrized boundary. This paper is meant to serve as a gentle introduction to the subject, and does not itself have immediate topologic…
Classifies objects in graded skew-gentle algebras using geometric models.
problem Classifying indecomposable objects in the derived category of graded skew-gentle algebras.
method Introduces new geometric models (punctured marked surfaces and binary surfaces) to classify objects.
result Integrates geometric models to classify objects in the derived category of graded skew-gentle algebras.
Improved LID for multilingual speakers using context-aware models.
problem Low accuracy for languages spoken by multilingual speakers, especially with accented speech.
method Coarser-grained acoustic model and integration with interaction context signals.
result Average 97% accuracy across all language combinations, 60% improvement in worst-case accuracy.
A tutorial on dynamic Laplacian for time-evolving data clusters.
problem Handling data with a time component and lying on a time-evolving manifold.
method Dynamic generalization of the Laplacian, SEBA algorithm for feature separation.
result Clusters correspond to long-lived coherent collections in time-evolving data.
The aim of this article is to present the category of bounded Frechet manifolds in respect to which we will review the geometry of Frechet manifolds with a stronger accent on its metric aspect. An inverse function theorem in the sense of Nash and Moser in this category is proved, and some applications to Riemannian geo…
New model for Calabi-Yau- categories using decorated marked surfaces.
problem Constructing models for Calabi-Yau- categories.
method Using graded decorated marked surfaces and string models.
result Isomorphism between braid twist group and spherical twist group.
Unified analysis of efficient local training methods for distributed variational inequalities.
problem Efficient distributed/federated learning for variational inequality problems.
method Unified convergence analysis of communication-efficient local training methods.
result First local gradient descent-accent algorithms with improved communication complexity.
This paper is a gentle introduction to some recent results involving the theory of gerbes over orbifolds for topologists, geometers and physicists. We introduce gerbes on manifolds, orbifolds, the Dixmier-Douady class, Beilinson-Deligne orbifold cohomology, Cheeger-Simons orbifold cohomology and string connections.
Getting Started with Particle Metropolis-Hastings for Inference in Nonlinear Dynamical Modelsstat.CO
This tutorial provides a gentle introduction to the particle Metropolis-Hastings (PMH) algorithm for parameter inference in nonlinear state-space models together with a software implementation in the statistical programming language R. We employ a step-by-step approach to develop an implementation of the PMH algorithm …
The aim of this paper is to provide a gentle introduction to Chabauty topology, while very little background knowledge is assumed. As an example, we provide pictures for the Chabauty space of C*. Note that the description of this space is not new; however the pictures are novel.
Introduces new gradient-based methods for machine learning problems.
problem New challenges in machine learning due to decision-making and multi-agent problems.
method Gradient-based optimization and variational inequalities.
result Shifts focus from pattern recognition to decision-making and multi-agent problems.
This post introduces model calibration and evaluation measures, highlighting issues with a common measure.
problem Ensuring model confidence accurately reflects true outcomes.
method Explains common calibration definition, ECE, and its drawbacks.
result New evaluation measures needed for comprehensive model calibration.
We study the cluster categories arising from marked surfaces (with punctures and non-empty boundaries). By constructing skewed-gentle algebras, we show that there is a bijection between tagged curves and string objects. Applications include interpreting dimensions of as intersection numbers of ta…
In this work, we argue that the implications of Pseudo and Quantum Random Number Generators (PRNG and QRNG) inexplicably affect the performances and behaviours of various machine learning models that require a random input. These implications are yet to be explored in Soft Computing until this work. We use a CPU and a …
Statistical learning theory provides the theoretical basis for many of today's machine learning algorithms. In this article we attempt to give a gentle, non-technical overview over the key ideas and insights of statistical learning theory. We target at a broad audience, not necessarily machine learning researchers. Thi…
Blockchain is a distributed database that keeps a chronologically-growing list (chain) of records (blocks) secure from tampering and revision. While computerisation has changed the nature of a ledger from clay tables in the old days to digital records in modern days, blockchain technology is the first true innovation i…
Nonnegative Matrix Factorization (NMF) was first introduced as a low-rank matrix approximation technique, and has enjoyed a wide area of applications. Although NMF does not seem related to the clustering problem at first, it was shown that they are closely linked. In this report, we provide a gentle introduction to clu…
Modeling structure in complex networks using Bayesian non-parametrics makes it possible to specify flexible model structures and infer the adequate model complexity from the observed data. This paper provides a gentle introduction to non-parametric Bayesian modeling of complex networks: Using an infinite mixture model …
Introduces non-abelian Hodge correspondence linking algebraic structures to geometry.
problem None explicitly stated, focuses on introduction.
method Pedagogical introduction of concepts linking algebraic structures to geometry.
result Explains the non-abelian Hodge correspondence and its connections.
We investigated the impact of noisy linguistic features on the performance of a Japanese speech synthesis system based on neural network that uses WaveNet vocoder. We compared an ideal system that uses manually corrected linguistic features including phoneme and prosodic information in training and test sets against a …
Paper proposes a new framework for SAD using GANs.
problem Speech Activity Detection (SAD) in diverse conditions.
method Joint learning with GANs and temporal discriminator.
result Framework outperforms state-of-the-art SAD approaches.
This guide introduces machine learning for medical data analysis.
problem Handling large, complex datasets in healthcare.
method Explains common machine learning algorithms and tasks.
result Illustrates machine learning applications in healthcare.
Study braid group actions on exceptional sequences using branched coverings.
problem Transitivity of braid group action on full exceptional sequences.
method Relate exceptional sequences to branched coverings, apply Birman--Hilden theory.
result Counterexamples to Bondal--Polishchuk conjecture on braid group transitivity.
This survey explores various optimality concepts in importance sampling.
problem Designing optimal proposal densities for Monte Carlo methods.
method Review of multiple frameworks and theoretical comparisons.
result Comprehensive understanding of optimality in importance sampling.
Teaches matrix calculus for machine learning and optimization.
problem Computing derivatives of functions involving matrices.
method Extends differential calculus to vector spaces, focusing on practical applications in machine learning.
result Introduction of adjoint and reverse-mode differentiation for efficient computation.
Determinantal point processes (DPPs) are elegant probabilistic models of repulsion that arise in quantum physics and random matrix theory. In contrast to traditional structured models like Markov random fields, which become intractable and hard to approximate in the presence of negative correlations, DPPs offer efficie…
This paper has two-fold goal: it provides gentle introduction to Knot Theory starting from 3-coloring, the concept introduced by R. Fox to allow undergraduate students to see that the trefoil knot is non-trivial, and ending with statistical mechanics. On the way we prove various (old and new) facts about knots. We rela…
CL methods improve monolingual ASR models across new tasks without forgetting past data.
problem Catastrophic Forgetting in monolingual ASR models when adapting to new domains or accents.
method Implement and compare various Continual Learning methods for monolingual ASR.
result Best CL method reduces performance gap by over 40% with minimal past data.
State-of-the-art solutions in the areas of "Language Modelling & Generating Text", "Speech Recognition", "Generating Image Descriptions" or "Video Tagging" have been using Recurrent Neural Networks as the foundation for their approaches. Understanding the underlying concepts is therefore of tremendous importance if we …
The Ma-Trudinger-Wang curvature --- or cross-curvature --- is an object arising in the regularity theory of optimal transportation. If the transportation cost is derived from a Hamiltonian action, we show its cross-curvature can be expressed in terms of the associated Jacobi fields. Using this expression, we show the l…
New neural network criterion connects RH to minimization problem.
problem Riemann Hypothesis (RH) about zeta function zeros.
method Revisits and extends Nyman-Beurling criterion linking RH to neural networks.
result Establishes connection between RH and minimization problem involving neural networks.
Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factor…
The first part of this text is a gentle exposition of some basic constructions and results in the extended prequantum theory of Chern-Simons-type gauge field theories. We explain in some detail how the action functional of ordinary 3d Chern-Simons theory is naturally localized ("extended", "multi-tiered") to a map on t…
Federated learning improves bioinformatics by sharing data legally.
problem Lack of access to diverse data in bioinformatics.
method Combines data from multiple institutions legally.
result Federated learning accelerates clinical discovery and robust exploration.
Method learns conditional distributions using neural entropic optimal transport.
problem Challenges in learning multiple conditional distributions.
method Neural entropic optimal transport method with two networks and regularization.
result Effective learning of conditional distributions with limited samples.
This book provides a gentle introduction to the study of arithmetic subgroups of semisimple Lie groups. This means that the goal is to understand the group SL(n,Z) and certain of its subgroups. Among the major results discussed in the later chapters are the Mostow Rigidity Theorem, the Margulis Superrigidity Theorem, R…
NLE embeds labels for domain adaptation with neural networks.
problem Adapting deep neural networks with unpaired source and target domain data.
method Distill source-domain knowledge into l-vectors, soft targets for adaptation.
result 14.1% relative word error rate reduction over direct re-training.
Spurred by the enthusiasm surrounding the "Big Data" paradigm, the mathematical and algorithmic tools of online optimization have found widespread use in problems where the trade-off between data exploration and exploitation plays a predominant role. This trade-off is of particular importance to several branches and ap…
This monograph presents the main complexity theorems in convex optimization and their corresponding algorithms. Starting from the fundamental theory of black-box optimization, the material progresses towards recent advances in structural optimization and stochastic optimization. Our presentation of black-box optimizati…
Introduces deep learning for graphs in a tutorial format.
problem Processing graph data efficiently and effectively.
method Top-down approach to graph representation learning with local and iterative processing.
result Generalized formulation and building blocks for graph neural models.