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.

168,742 papers · 148 categories

Trend · papers per month

14284155 · Jun 202019922001200920172026
48 results for NAT translation

This work improves NAT translation accuracy through fine-tuning with curriculum learning.

problem Improving NAT translation accuracy while maintaining inference speed.
method Curriculum learning applied to fine-tuning of a pre-trained AT model to a NAT model.
result Significant improvement in translation accuracy (over 1 BLEU score) and speedup in inference.

As a new neural machine translation approach, Non-Autoregressive machine Translation (NAT) has attracted attention recently due to its high efficiency in inference. However, the high efficiency has come at the cost of not capturing the sequential dependency on the target side of translation, which causes NAT to suffer …

2019-02-22abs ↗pdf ↗

Proposes a method to improve neural architectures reproducibly.

problem Lack of reproducibility in Neural Architecture Transformer (NAT).
method Differentiable Neural Architecture Transformation (DNAT).
result DNAT outperforms NAT and is applicable to various models and datasets.

In the past few years, neural abstractive text summarization with sequence-to-sequence (seq2seq) models have gained a lot of popularity. Many interesting techniques have been proposed to improve seq2seq models, making them capable of handling different challenges, such as saliency, fluency and human readability, and ge…

2018-12-05abs ↗pdf ↗

New bounds show agnostic multiclass learning depends on two dimensions: Natarajan and Daniely-Shalev-Shwartz.

problem Understanding sample complexity in multiclass classification with agnostic learning.
method Developed a novel online procedure based on a self-adaptive multiplicative-weights algorithm.
result Agnostic sample complexity bounds are in the form of DS^(1.5)/ε + Nat/ε^2, nearly tight up to a √DS factor.

Learning latent variable models with stochastic variational inference is challenging when the approximate posterior is far from the true posterior, due to high variance in the gradient estimates. We propose a novel rejection sampling step that discards samples from the variational posterior which are assigned low likel…

2018-04-05abs ↗pdf ↗

We show that within the class of left-invariant naturally reductive metrics MNat(G)\mathcal{M}_{\operatorname{Nat}}(G) on a compact simple Lie group GG, every metric is spectrally isolated. We also observe that any collection of isospectral compact symmetric spaces is finite; this follows from a somewhat stronger statement…

2007-07-05abs ↗pdf ↗

New memory allocation scheme improves image generation performance.

problem Improving episodic and semantic memory representation in neural networks.
method Developed a hierarchical latent variable model with differentiable, locally block allocated latent memory.
result Improved conditional likelihood values on various datasets.

Convolutional neural networks provide visual features that perform remarkably well in many computer vision applications. However, training these networks requires significant amounts of supervision. This paper introduces a generic framework to train deep networks, end-to-end, with no supervision. We propose to fix a se…

2017-04-18abs ↗pdf ↗

Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning. Many real life data sets contain a small amount of labelled data points, that are typically disregarded when training generative models. We propose the Cluster-aware Generative Mod…

2017-04-03abs ↗pdf ↗

DSPPs improve predictive distributions in scalable regression tasks.

problem Improving predictive distributions in scalable regression tasks.
method Inspired by DGPs, DSPPs use mini-batch training and kernel basis functions for uncertainty control.
result DSPPs provide significantly better calibrated predictive distributions than other methods.

The combination of inducing point methods with stochastic variational inference has enabled approximate Gaussian Process (GP) inference on large datasets. Unfortunately, the resulting predictive distributions often exhibit substantially underestimated uncertainties. Notably, in the regression case the predictive varian…

2019-10-16abs ↗pdf ↗

Study on rigidity of translating hypersurfaces not in graphical direction.

problem Rigidity of translating hypersurfaces not in graphical direction.
method Proved rigidity results for complete graphical translating hypersurfaces under specific conditions.
result Entire graphical translating surfaces are flat under certain conditions.

The natural automorphism group of a translation surface is its group of translations. For finite translation surfaces of genus g > 1 the order of this group is naturally bounded in terms of g due to a Riemann-Hurwitz formula argument. In analogy with classical Hurwitz surfaces, we call surfaces which achieve the maxima…

2013-11-28abs ↗pdf ↗

Study on stable translation lengths of surface homeomorphisms and their approximations.

problem Understanding stable translation lengths of homeomorphisms and their finite approximations.
method Comparing stable translation lengths of homeomorphisms and their finite approximations on curve graphs.
result Stable translation length of homeomorphisms with dense periodic points equals the supremum of their approximations.

Study measures gender bias in machine translation using multiple reference points.

problem Measuring and identifying gender bias in machine translation.
method Used an optimal non-biased translator, reference points from occupational statistics and survey.
result Found bias against both genders, but more against women, and found occupations have a greater effect than adjectives.

This paper uses LLMs and cycle consistency for better machine translation evaluation.

problem Evaluating translation quality and LLM capabilities without ground truth.
method Generate translation candidates, back-translate, and evaluate cycle consistency.
result Larger LLMs or more inference passes improve cycle consistency.

Paper finds a non-existence theorem for certain translators in high dimensions.

problem Non-existence of certain translators in high-dimensional spaces.
method Developed a non-existence theorem and found an example of a translator.
result Non-existence of entire Qn1Q_{n-1}-translators in Rn+1\mathbb{R}^{n+1}.

Constructing translating solitons from Lagrangian Grim Reapers.

problem Creating Lagrangian translating solitons from intersections of Grim Reapers.
method Desingularizing intersections with special Lagrangian Lawlor necks.
result Constructing Lagrangian translating solitons with multiple ends and loops.

Study on singular points of translation surfaces under linearly dependent conditions.

problem Investigate singular points of translation surfaces under linearly dependent conditions.
method Use theories of generalised framed surfaces and framed surfaces.
result Introduce translation generalised framed surfaces and investigate their singular points.

In this article we prove two non-existence results for translating solitons of the mean curvature flow (translators for short) in Rm+1\mathbb{R}^{m+1}. We also obtain an upper bound to the maximum height that a compact embedded translator in R3\mathbb{R}^{3} can achieve. On the other hand, we study graphical perturbation…

2016-01-27abs ↗pdf ↗

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural ma…

2014-09-01abs ↗pdf ↗

Study invariant λλ-translators in Lorentz-Minkowski space.

problem Characterize λλ-translators invariant under translations and rotations.
method Analyze 1-parameter group of translations and rotations, find explicit parametrizations, and solve non-linear autonomous systems.
result Explicit parametrizations and qualitative properties of invariant λλ-translators.

Study classifies and characterizes translators in hyperbolic static universe.

problem Classifying and characterizing translators in hyperbolic static universe.
method Classified and characterized translators foliated by horospheres and rotationally invariant ones, both space-like and time-like.
result Obtained a characterization of the bowl and certain translators foliated by horospheres.

The study proves stability of various graphical translators in mean curvature flow.

problem Stability of graphical translators in mean curvature flow.
method Existence of longtime solution to mean curvature flow, dynamical stability results for various graphical translators.
result Dynamical stability of various types of graphical translators.

Study translators in Generalised Robertson-Walker spacetimes, identifying warping functions and classifying examples.

problem Understanding translators in Generalised Robertson-Walker spacetimes.
method Analyzing translators as submanifolds satisfying the mean curvature flow equation with a specific vector field.
result Identification of three one-parameter families of warping functions and classification of translators.

The paper shows how integrating categorical semantics can enhance unsupervised domain translation.

problem Improving unsupervised domain translation between perceptually different domains.
method Learning invariant categorical semantic features in an unsupervised manner and conditioning them on the style encoder.
result Conditioning the style encoder on learned categorical semantics improves translation and stylization.