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.
Partial soft-matching distance improves neural representation comparison by allowing some neurons to remain unmatched.
End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is due to a key technique called attention mechanisms, and all successful methods proposed so far have been based on soft attention mechanisms. H…
Comparing data defined over space and time is notoriously hard, because it involves quantifying both spatial and temporal variability, while at the same time taking into account the chronological structure of data. Dynamic Time Warping (DTW) computes an optimal alignment between time series in agreement with the chrono…
We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy. Unlike the Euclidean distance, DTW can compare time series of variable size and is robust to shifts or dilatations across the time dimension. To compute DTW, one typically so…
Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain. In this paper, we propose a Soft Transfer Network (STN), which jointly learns a domain-shared classifier and a domain-invariant subspace in an end-to-end manner, for a…
A new framework for averaging spatio-temporal signals using optimal transport and soft alignments.
GSI improves efficiency of large language model inference.
EAST aligns neural network classifiers with user-defined evaluation metrics.
New method improves stability of soft FQI for offline RL.
Soft geometric bias improves physical dynamics predictions.
A new method for unsupervised domain adaptation using manifold learning.
Sequence-to-sequence text-to-speech (TTS) is dominated by soft-attention-based methods. Recently, hard-attention-based methods have been proposed to prevent fatal alignment errors, but their sampling method of discrete alignment is poorly investigated. This research investigates various combinations of sampling methods…
Existing deep multitask learning (MTL) approaches align layers shared between tasks in a parallel ordering. Such an organization significantly constricts the types of shared structure that can be learned. The necessity of parallel ordering for deep MTL is first tested by comparing it with permuted ordering of shared la…
Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To address these issues, we propose Monotonic Chunkwise Attention (MoChA), which adaptiv…
Deep Neural Network (DNN) acoustic models have yielded many state-of-the-art results in Automatic Speech Recognition (ASR) tasks. More recently, Recurrent Neural Network (RNN) models have been shown to outperform DNNs counterparts. However, state-of-the-art DNN and RNN models tend to be impractical to deploy on embedde…
A novel method for comparing graphs of different sizes using Wasserstein distance.
Proposes a framework to improve domain adaptation without labeled data.
The abstract explores connections between reinforcement learning, scaling, and diffusion.
Fusion of transformer networks using optimal transport for improved performance.
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…
Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are aligned at each time step. Our new differentiable sampling algorithm addresses this…
Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does not marginalize over latent alignments in a probabilistic sense. This property …
New method generates plausible counterfactuals for time series classification.
Improved inference-time alignment using Best-of-N and smoothing.
New method distills cloud models into edge-friendly ones.
New metric captures individual neuron tuning across neural networks.
Proposes DFDG for robust domain generalization without source domain labels.
This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft correspondences between nodes. Secondly, we employ synchronous message passing networks …
SelectMix improves deep learning robustness against noisy labels.
Monte Carlo methods are widely used in particle physics to integrate and sample probability distributions (differential cross sections or decay rates) on multi-dimensional phase spaces. We present a Neural Network (NN) algorithm optimized to perform this task. The algorithm has been applied to several examples of direc…
Employers actively look for talents having not only specific hard skills but also various soft skills. To analyze the soft skill demands on the job market, it is important to be able to detect soft skill phrases from job advertisements automatically. However, a naive matching of soft skill phrases can lead to false pos…
Optimal control of reserve assets for stablecoins to maintain peg stability.
This study improves knowledge distillation for RNN-T models with noisy labels.
Soft labeling impacts OOD detection in neural networks.
Developed a new thresholding method that connects soft and hard thresholding.
In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a new …
Soft cells fill space without gaps, derived from minimal surfaces and deformed using edge bending.
ASBART accelerates Soft BART for faster Bayesian regression.
Maximum entropy deep reinforcement learning (RL) methods have been demonstrated on a range of challenging continuous tasks. However, existing methods either suffer from severe instability when training on large off-policy data or cannot scale to tasks with very high state and action dimensionality such as 3D humanoid l…
We propose JECL, a method for clustering image-caption pairs by training parallel encoders with regularized clustering and alignment objectives, simultaneously learning both representations and cluster assignments. These image-caption pairs arise frequently in high-value applications where structured training data is e…
Generalizes soft noncommutative schemes to flag varieties.
Paper proposes a new loss function for conditional models using soft targets.
Tutorial on optimizing diffusion model samples for specific metrics.
Introduces Soft-SVM for binary classification bridging logistic and SVM.
Deep model learns from labeled and unlabeled data for industrial soft sensing.
This paper introduces TNTK to study infinite soft tree ensembles.
Improves deep neural networks using soft labels through alternating minimization.
The paper develops a multi-unit soft sensing model for virtual flow meters that improves few-shot learning.