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

3517021,0521,403 · Jun 202019922001200920172026
48 results for transducer model

Improved neural transducer model outperforms attention model on longer sequences.

problem Improving performance of neural transducer models.
method Comparison of training criteria (marginalization vs. maximum approximation), model generalization, and output label topology.
result Final transducer model outperforms attention model by over 6% relative WER on Switchboard 300h.

Conditional random fields (CRFs) have been shown to be one of the most successful approaches to sequence labeling. Various linear-chain neural CRFs (NCRFs) are developed to implement the non-linear node potentials in CRFs, but still keeping the linear-chain hidden structure. In this paper, we propose NCRF transducers, …

2018-11-04abs ↗pdf ↗

A new method calculates optimal decisions from classifier outputs, improving predictions in drug discovery.

problem Finding optimal decisions from classifier outputs in fields like medicine.
method Develops a transducer that calculates probabilities from classifier outputs, enabling expected-utility maximization.
result Improves prediction accuracy in drug discovery problems, sometimes close to theoretical maximum.

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in performance compared to non-streaming models such as Listen, Attend and Spell (…

2017-12-05abs ↗pdf ↗

New methods improve integration of external LMs with AED models.

problem Improving performance of AED models by integrating external LMs.
method Comparing and proposing novel methods to estimate implicit LM from AED models.
result Proposed methods outperform previous approaches.

A fixed point theorem is proved for inverse transducers, leading to an automata-theoretic proof of the fixed point subgroup of an endomorphism of a finitely generated virtually free group being finitely generated. If the endomorphism is uniformly continuous for the hyperbolic metric, it is proved that the set of regula…

2012-03-07abs ↗pdf ↗

We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms. This penalty term is an effective regularizer for RNNs including LSTMs and IRNNs, improving performance on character-level language modeling and phoneme recognition, and outperfor…

2015-11-26abs ↗pdf ↗

This paper formalizes Uniswap v3 using PTA and FST for rigorous analysis.

problem Formal modeling of Uniswap v3's concentrated liquidity for rigorous analysis.
method Formal state machine models using PTA and FST, proving rounding bounds.
result Formal justification of Uniswap v3's εε-slack and rounding safety.

Most of the parameters in large vocabulary models are used in embedding layer to map categorical features to vectors and in softmax layer for classification weights. This is a bottle-neck in memory constraint on-device training applications like federated learning and on-device inference applications like automatic spe…

2018-11-20abs ↗pdf ↗

Conformal Prediction Regions match Imprecise Highest Density Regions under consonance.

problem Matching conformal prediction regions with highest density regions.
method Using consonance and the Imprecise Probability theory of clouds.
result Imprecise Highest Density Regions are equivalent to Conformal Prediction Regions under consonance.

Requirements elicitation can be very challenging in projects that require deep domain knowledge about the system at hand. As analysts have the full control over the elicitation process, their lack of knowledge about the system under study inhibits them from asking related questions and reduces the accuracy of requireme…

2018-07-10abs ↗pdf ↗

A keyword spotting (KWS) system determines the existence of, usually predefined, keyword in a continuous speech stream. This paper presents a query-by-example on-device KWS system which is user-specific. The proposed system consists of two main steps: query enrollment and testing. In query enrollment step, phonetic pos…

2019-10-11abs ↗pdf ↗

We propose a method for modeling and learning turn-taking behaviors for accessing a shared resource. We model the individual behavior for each agent in an interaction and then use a multi-agent fusion model to generate a summary over the expected actions of the group to render the model independent of the number of age…

2018-12-10abs ↗pdf ↗

New ASR system handles multiple languages without needing language-specific encoding.

problem Joint training of data-rich and data-scarce languages in a single model.
method Transforms all languages to a single writing system through transliteration, separating modeling and rendering.
result Language-agnostic multilingual ASR system reduces WER up to 10% over language-dependent models.

This study improves knowledge distillation for RNN-T models with noisy labels.

problem Challenges in distilling knowledge from RNN-T models with variable quality teachers.
method Full-sum distillation and sequence-level knowledge distillation.
result Full-sum distillation outperforms other methods for RNN-T models, especially for bad teachers.

The paper introduces BCART models for aggregate claim amount, improving frequency-severity and joint modeling.

problem Modeling aggregate claim amount with frequency-severity and joint dependencies.
method Developed three types of BCART models: frequency-severity, sequential, and joint models. Used various distributions for claim severity data.
result Weibull distribution outperforms gamma and lognormal for right-skewed, heavy-tailed claim severity data.

The paper uses model-based trees to create interpretable surrogate models for complex machine learning models.

problem Interpreting complex machine learning models.
method Using model-based trees to partition feature space and create interpretable models.
result Model-based trees generate optimal surrogate models that balance interpretability and performance.

The study examines how model predictions hold up under model extensions.

problem Model predictions may not be robust under model extensions, limiting their applicability.
method The study uses causal ordering to assess robustness of qualitative model predictions and characterizes model extensions that preserve predictions.
result Conditions and techniques are provided to assess robustness of model predictions under model extensions.

Revises Bayesian model averaging for foundation models.

problem Ensemble pre-trained and lightly-finetuned foundation models for improved classification performance.
method Introduces trainable linear classifiers and computationally cheaper model averaging scheme (OMA).
result Ensembled models can better predict on various datasets.

Paper introduces symmetric divergence link models for probability distributions.

problem Symmetric divergence measures for probability distributions.
method Two general classes of link models: one for survival functions and another for cumulative probability distribution functions.
result Advantages of symmetric divergence measures over asymmetric measures for model averaging and feature assessment.

Researchers review challenges in interpreting additive models, especially neural additive models.

problem Challenges in interpreting additive models, particularly neural additive models.
method Review of generalized additive models and discussion of nonidentifiability.
result Challenges in claiming interpretability or suitability for safety-critical applications of additive models.

Sigma models linked to Gross-Neveu models via quiver varieties.

problem Understanding the relationship between sigma models and Gross-Neveu models.
method Exploring the mathematical correspondence between sigma models and Gross-Neveu models, including their geometric and trigonometric/elliptic deformations.
result Sigma models are mathematically equivalent to Gross-Neveu models under certain conditions.

Simple models are preferred over complex models, but over-simplistic models could lead to erroneous interpretations. The classical approach is to start with a simple model, whose shortcomings are assessed in residual-based model diagnostics. Eventually, one increases the complexity of this initial overly simple model a…

2017-06-26abs ↗pdf ↗

Matryoshka hides secret models in a carrier model, achieving high capacity and robustness.

problem Stealing functionality of private ML data by hiding models in a carrier model.
method Parameter sharing approach exploiting the learning capacity of the carrier model.
result Hides a 26x larger secret model or 8 secret models in the carrier model.

This work develops scalable model selection methods with fast update and selection.

problem Efficient model selection for large pools of candidate models.
method Isolated model embedding, which supports asymptotically fast update and selection.
result Standardized Embedder achieves competitive model selection performances.

Copulas outperform marginal models in multivariate risk forecasting, reducing model risk by narrowing down the set of models.

problem Model risk in multivariate risk forecasting, especially during crises.
method Comprehensive empirical study comparing Copula-GARCH models with fixed marginals, copulas, or neither.
result Model risk is almost entirely due to copula choice, not marginal models.

This paper distills a complex travel mode choice model into simpler, interpretable models.

problem Lack of interpretability in complex machine learning models for travel behavior.
method Model distillation combined with market segmentation.
result Generated interpretable models that closely match the predictions of the original complex model.

BayesBlend blends multiple models' predictions for better insurance loss predictions.

problem Improving insurance loss predictions by combining multiple models.
method Pseudo-Bayesian model averaging, stacking, and hierarchical stacking.
result BayesBlend provides a user-friendly way to blend model predictions and estimate weights.

The paper identifies when larger models improve predictions and proposes a switcher model.

problem Understanding when larger models benefit from added complexity.
method Numerical studies on T5 architecture to analyze predictive uncertainty and model performance.
result Large models improve on examples where small models are uncertain, but not on certain examples.

Aggregates models from different datasets using shared latent structures.

problem Aggregating models from heterogeneous datasets with shared latent structures.
method Bayesian nonparametrics for identifying correspondences among local model parameterizations.
result Framework successfully aggregates various model types across different applications.