Research
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.

168,657 papers · 148 categories

Trend · papers per month

3875113150 · Jun 202019922001200920172026
48 results for end

Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving end-to-end models in other domains. However, they are relatively under explored for end-to-end speech models. Therefore, we investigate the e…

2017-12-19abs ↗pdf ↗

Develops Bayesian approach for end-to-end learning in stochastic optimization.

problem Stochastic optimization problems under uncertainty.
method Bayesian interpretation and new end-to-end learning algorithms.
result Improved decision maps for empirical risk minimization and distributionally robust optimization.

Study shows mapping class groups are one-ended for surfaces with at least one end.

problem Analyzing the number of ends in mapping class groups of surfaces.
method Proving the associated translatable curve graph is one-ended, quasi-isometric to the mapping class group.
result Mapping class groups are one-ended for surfaces with at least one end of discrete type.

End-to-end autonomous driving models get better uncertainty estimates.

problem Uncertainty quantification for end-to-end autonomous driving models.
method Approximate inference for implicit copula neural linear model.
result Densities for steering angle are marginally calibrated.

This work proposes splitting deep neural networks into smaller sub-networks for faster and more efficient distillation.

problem Challenges in training deep neural networks, including local optima, gradient issues, and computational demands.
method Proposes a non-end-to-end distillation approach by splitting networks into smaller, independent sub-networks (neighbourhoods).
result Independent training of smaller sub-networks can speed up distillation and improve efficiency in various applications.

End-to-end learning refers to training a possibly complex learning system by applying gradient-based learning to the system as a whole. End-to-end learning system is specifically designed so that all modules are differentiable. In effect, not only a central learning machine, but also all "peripheral" modules like repre…

2017-04-26abs ↗pdf ↗

End-to-end autonomous driving perception learns latent features for better performance.

problem Current autonomous driving systems are complex and require human engineering.
method Sequential latent representation learning for end-to-end perception.
result End-to-end perception model solves detection, tracking, localization, and mapping problems.

Kauri is a novel unsupervised binary tree for clustering that outperforms existing methods.

problem Learning a tree end-to-end for clustering without labels is an open challenge.
method Greedy maximization of the kernel KMeans objective without centroids.
result Kauri often outperforms existing unsupervised clustering methods, especially with non-linear kernels.

End-to-end solution for recognizing handwritten numerals, avoiding traditional preprocessing steps.

problem Handwritten numeral string recognition with traditional preprocessing steps.
method YoLo-based model for automatic detection and recognition, avoiding heuristic-based preprocessing and segmentation.
result Proposed method reduces complexity and is a feasible end-to-end solution for numeral string recognition.

End-to-end audio recognition system improves accuracy.

problem Improving accuracy in auditory object recognition.
method Proposes an end-to-end deep neural network with an 'inception nucleus' to learn features from raw waveforms.
result Bests current state-of-the-art approaches by 10.4 percentage points on Urbansound8k dataset.

Derives an index formula for families of end-periodic Dirac operators.

problem Calculating the index of families of end-periodic Dirac operators.
method Using the renormalized Chern character and Fourier-Laplace transform of the Bismut superconnection.
result Establishes an index formula involving a new end-periodic eta form.

Free groups can be end homogeneity groups of 3-manifolds.

problem Tackling the possibility of free groups as end homogeneity groups of 3-manifolds.
method Constructing specific 3-manifolds with end homogeneity groups isomorphic to free groups.
result For every finitely generated free group, there exists an irreducible open 3-manifold with that group as its end homogeneity group.

Recent work on discriminative segmental models has shown that they can achieve competitive speech recognition performance, using features based on deep neural frame classifiers. However, segmental models can be more challenging to train than standard frame-based approaches. While some segmental models have been success…

2016-10-21abs ↗pdf ↗

Study of ends of complete gradient Schouten solitons, showing finitely many ends for shrinking and connected infinity for expanding ones.

problem Characterizing the ends of complete gradient Schouten solitons.
method Analysis of ends without additional assumptions, focusing on shrinking and expanding cases.
result Finitely many ends for shrinking Schouten solitons and connected infinity for expanding ones.

End-to-end Text-to-speech (TTS) system can greatly improve the quality of synthesised speech. But it usually suffers form high time latency due to its auto-regressive structure. And the synthesised speech may also suffer from some error modes, e.g. repeated words, mispronunciations, and skipped words. In this paper, we…

2018-12-12abs ↗pdf ↗

Two results on end spaces of infinite type surfaces, answering questions about their topology and equivalence.

problem Topology and equivalence of end spaces of infinite type surfaces.
method Examples and Tsankov's argument to show equivalence relation.
result Examples of infinite type surfaces with end spaces that are not self-similar but have a unique maximal type.

We show that an Osserman-type inequality holds for spacelike surfaces of constant mean curvature (CMC) 1 with singularities and with elliptic ends in de Sitter 3-space. An immersed end of a CMC 1 surface is an ``elliptic end'' if the monodromy representation at the end is diagonalizable with eigenvalues in the unit cir…

2004-08-03abs ↗pdf ↗

Recent studies have introduced end-to-end TTS, which integrates the production of context and acoustic features in statistical parametric speech synthesis. As a result, a single neural network replaced laborious feature engineering with automated feature learning. However, little is known about what types of context in…

2018-11-04abs ↗pdf ↗

Embeddings of mapping tori for end-periodic graph maps are proven.

problem Embedding mapping tori of end-periodic graph maps into finite complexes.
method Flowline-preserving homotopy equivalence and π1π_1-injective map.
result Every mapping class of Γ arising from an end-periodic homotopy equivalence contains a representative whose mapping torus realizes such an embedding.

End-to-end approach for weak supervision improves downstream model performance.

problem Data-labeling bottleneck in machine learning applications.
method Directly learning the downstream model by maximizing its agreement with probabilistic labels generated from weak supervision sources.
result Improved performance over prior work in terms of downstream model performance and robustness.

WEEND uses a neural network to recognize speech and assign speakers to words.

problem End-to-end neural diarization without additional ASR and orchestration.
method Multi-task learning with an auxiliary network for ASR and speaker diarization.
result WEEND outperforms turn-based diarization and can handle 5-minute audio.

Real projective structures on nn-orbifolds are useful in understanding the space of representations of discrete groups into SL(n+1,R)\mathrm{SL}(n+1, \mathbb{R}) or PGL(n+1,R)\mathrm{PGL}(n+1, \mathbb{R}). A recent work shows that many hyperbolic manifolds deform to manifolds with such structures not projectively equivalent to the o…

2015-01-02abs ↗pdf ↗

For a complete minimal surface in the Euclidean 3-space, the so-called flux vector corresponds to each end. The flux vectors are balanced, i.e., the sum of those over all ends are zero. Consider the following inverse problem: For each balanced n vectors, find an n-end catenoid which attains given vectors as flux. Here,…

1997-09-02abs ↗pdf ↗

HabitatAgent offers a multi-agent system for transparent housing consultation.

problem Opaque reasoning and brittle multi-constraint handling in housing recommendation systems.
method HabitatAgent is a multi-agent architecture with specialized roles for memory, retrieval, generation, and validation.
result HabitatAgent achieves 95% accuracy in real user consultation scenarios, significantly outperforming a strong baseline.

Guided Learning improves end-to-end modeling for multi-stage decision-making.

problem Challenges in training unified neural networks for multi-stage decision-making.
method Guided Learning framework with a guide function and utility function.
result Significant improvement in performance over traditional methods.