arXiv research

A new weighted FDA method improves face recognition accuracy.

Structured weight pruning is a representative model compression technique of DNNs to reduce the storage and computation requirements and accelerate inference. An automatic hyperparameter determination process is necessary due to the large number of flexible hyperparameters. This work proposes AutoCompress, an automatic…

This work presents an approach to automatically induction for non-greedy decision trees constructed from neural network architecture. This construction can be used to transfer weights when growing or pruning a decision tree, allowing non-greedy decision tree algorithms to automatically learn and adapt to the ideal arch…

In the classic sparsity-driven problems, the fundamental L-1 penalty method has been shown to have good performance in reconstructing signals for a wide range of problems. However this performance relies on a good choice of penalty weight which is often found from empirical experiments. We propose an algorithm called t…

Improves Gower's similarity for mixed-type variables with automatic weighting.

Automatic text summarization tools have a great impact on many fields, such as medicine, law, and scientific research in general. As information overload increases, automatic summaries allow handling the growing volume of documents, usually by assigning weights to the extracted phrases based on their significance in th…

This paper optimizes deep learning training by efficiently sharding weight updates across replicas.

Automates zero-shot classification by scoring and weighting prompts.

We present an Automatic Relevance Determination prior Bayesian Neural Network(BNN-ARD) weight l2-norm measure as a feature importance statistic for the model-x knockoff filter. We show on both simulated data and the Norwegian wind farm dataset that the proposed feature importance statistic yields statistically signific…

We introduce a financial portfolio optimization framework that allows us to automatically select the relevant assets and estimate their weights by relying on a sorted $\ell_1$-Norm penalization, henceforth SLOPE. Our approach is able to group constituents with similar correlation properties, and with the same underlyin…

The use of automatic methods, often referred to as Neural Architecture Search (NAS), in designing neural network architectures has recently drawn considerable attention. In this work, we present an efficient NAS approach, named HM- NAS, that generalizes existing weight sharing based NAS approaches. Existing weight shar…

Python package automates causal parameter estimation using Riesz regression.

DoWG optimizer automatically adapts to convex and nonsmooth problems without tuning.

In this paper we introduce various techniques to improve the performance of electroencephalography (EEG) features based continuous speech recognition (CSR) systems. A connectionist temporal classification (CTC) based automatic speech recognition (ASR) system was implemented for performing recognition. We introduce tech…

AutoKE automates embedding physical knowledge into neural networks for complex engineering problems.

Improved robustness in ASR systems with speaker adaptation.

Adaptive weighting schemes enhance time-series data augmentation for financial and UCR datasets.

Proposes new methods for interpreting document classification models.

A common strategy for sparse linear regression is to introduce regularization, which eliminates irrelevant features by letting the corresponding weights be zeros. However, regularization often shrinks the estimator for relevant features, which leads to incorrect feature selection. Motivated by the above-mentioned issue…

Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of "co-adapted" weights to it being a form of cheap Bayesian inference. We propose a novel framework for understanding multiplicative noise in neural net…

New algorithm improves causal effect estimation for continuous treatments.

As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and computational resources, such as voice command recognition in vehicles and robot interact…

This paper improves auto-augment efficiency by sharing augmentation weights.

With the success of deep neural networks, Neural Architecture Search (NAS) as a way of automatic model design has attracted wide attention. As training every child model from scratch is very time-consuming, recent works leverage weight-sharing to speed up the model evaluation procedure. These approaches greatly reduce …

A method makes particle filters differentiable without altering their forward pass.

This paper introduces a spline-based method for nonparametric ADVI that handles complex posterior distributions.

A novel neural network training method reduces gradient variance for faster and better reinforcement learning.

Automatically learns flexible symmetry constraints in neural networks using gradients.

Adversarial domain-invariant training (ADIT) proves to be effective in suppressing the effects of domain variability in acoustic modeling and has led to improved performance in automatic speech recognition (ASR). In ADIT, an auxiliary domain classifier takes in equally-weighted deep features from a deep neural network …

Quantifying the degree of atrophy is done clinically by neuroradiologists following established visual rating scales. For these assessments to be reliable the rater requires substantial training and experience, and even then the rating agreement between two radiologists is not perfect. We have developed a model we call…

This work extends neural networks to automatically select features by stochastically penalizing feature involvement.

Develops STC for sequential data with missing labels.

This work proposes a new algorithm for training a re-weighted L2 Support Vector Machine (SVM), inspired on the re-weighted Lasso algorithm of Candès et al. and on the equivalence between Lasso and SVM shown recently by Jaggi. In particular, the margin required for each training vector is set independently, defining a n…

Guaranteed bounds for posterior inference in probabilistic programs.

Much of the focus in machine learning research is placed in creating new architectures and optimization methods, but the overall loss function is seldom questioned. This paper interprets machine learning from a multi-objective optimization perspective, showing the limitations of the default linear combination of loss f…

In cognitive psychology, automatic and self-reinforcing irrational thought patterns are known as cognitive distortions. Left unchecked, patients exhibiting these types of thoughts can become stuck in negative feedback loops of unhealthy thinking, leading to inaccurate perceptions of reality commonly associated with anx…

How can one perform Bayesian inference on stochastic simulators with intractable likelihoods? A recent approach is to learn the posterior from adaptively proposed simulations using neural network-based conditional density estimators. However, existing methods are limited to a narrow range of proposal distributions or r…

ETM identifies field-specific keywords in text classification.

We continue to develop our neural network (NN) based forecasting approach to anomaly detection (AD) using the Secure Water Treatment (SWaT) industrial control system (ICS) testbed dataset. We propose genetic algorithms (GA) to find the best NN architecture for a given dataset, using the NAB metric to assess the quality…

We examine the effect of the Group Lasso (gLasso) regularizer in selecting the salient nodes of Deep Neural Network (DNN) hidden layers by applying a DNN-HMM hybrid speech recognizer to TED Talks speech data. We test two types of gLasso regularization, one for outgoing weight vectors and another for incoming weight vec…

Hybrid regularization avoids double descent in random feature models.

Optimization algorithms with momentum, e.g., (ADAM), have been widely used for building deep learning models due to the faster convergence rates compared with stochastic gradient descent (SGD). Momentum helps accelerate SGD in the relevant directions in parameter updating, which can minify the oscillations of parameter…

We examine how recently documented, fundamental phenomena in deep learning models subject to pruning are affected by changes in the pruning procedure. Specifically, we analyze differences in the connectivity structure and learning dynamics of pruned models found through a set of common iterative pruning techniques, to …

This paper develops a weighted $L^2$-method for the (half) Dirac equation. For Dirac bundles over closed Riemann surfaces, we give a sufficient condition for the solvability of the (half) Dirac equation in terms of a curvature integral. Applying this to the Dolbeault-Dirac operator, we establish an automatic transversa…

Bayesian deep learning with heavy-tailed weights achieves near-optimal performance.

In recent years, deep neural networks (DNNs) have been applied to various machine leaning tasks, including image recognition, speech recognition, and machine translation. However, large DNN models are needed to achieve state-of-the-art performance, exceeding the capabilities of edge devices. Model reduction is thus nee…

A classification of companies into sectors of the economy is important for macroeconomic analysis and for investments into the sector-specific financial indices and exchange traded funds (ETFs). Major industrial classification systems and financial indices have historically been based on expert opinion and developed ma…

A popular regularized (shrinkage) covariance estimator is the shrinkage sample covariance matrix (SCM) which shares the same set of eigenvectors as the SCM but shrinks its eigenvalues toward its grand mean. In this paper, a more general approach is considered in which the SCM is replaced by an M-estimator of scatter ma…