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

24487195 · Jun 202019922001200920172026
48 results for ensemble distillation

Study on ensemble, distillation, and self-distillation in deep learning models.

problem Improving test accuracy in deep learning models using ensemble and distillation methods.
method Formal study of ensemble and distillation, considering multi-view data structure.
result Proven that ensemble and distillation can improve test accuracy in deep learning models, and the superior performance can be distilled into a single model.

Ensembles of neural networks have been shown to give better performance than single networks, both in terms of predictions and uncertainty estimation. Additionally, ensembles allow the uncertainty to be decomposed into aleatoric (data) and epistemic (model) components, giving a more complete picture of the predictive u…

2020-02-26abs ↗pdf ↗

Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory. Therefore, recent research has focused on distilling ensembles into a single compact model, reducing the computational and memory burden o…

2020-01-14abs ↗pdf ↗

Ensembles of models often yield improvements in system performance. These ensemble approaches have also been empirically shown to yield robust measures of uncertainty, and are capable of distinguishing between different \emph{forms} of uncertainty. However, ensembles come at a computational and memory cost which may be…

2019-04-30abs ↗pdf ↗

Paper proposes ensemble distillation for well-calibrated structured prediction.

problem Well-calibrated predictions are hard to achieve in structured prediction.
method Ensemble distillation framework for structured prediction.
result Ensemble distillation produces well-calibrated models with similar performance and calibration benefits to ensembles.

FAST-DAD distills complex ensemble models into faster, more accurate individual models.

problem Deploying complex AutoML ensemble predictors on tabular data is slow, large, and opaque.
method Data augmentation strategy based on Gibbs sampling from a self-attention pseudolikelihood estimator.
result FAST-DAD distillation produces significantly better individual models than standard training.

S2D efficiently trains models to estimate uncertainty without increasing resource costs.

problem Efficiently estimating uncertainty in deep learning models for safety-critical applications.
method Self-distribution distillation (S2D) approach to train a single model for uncertainty estimation.
result S2D models outperform standard models and Monte-Carlo dropout in uncertainty estimation.

Anti-Distillation improves reproducibility of deep networks by making ensemble predictions more diverse.

problem Deep networks are prone to high prediction differences, making them less reproducible.
method Anti-Distillation uses ensembles to force predictions to be more different and diverse.
result Anti-Distillation reduces prediction differences by making ensemble predictions more diverse.

Regression Prior Networks improve ensemble performance on regression tasks.

problem Improving ensemble performance on regression tasks.
method Extending Prior Networks and Ensemble Distribution Distillation (EnD2^2) to regression tasks using the Normal-Wishart distribution.
result Regression Prior Networks yield performance competitive with ensemble approaches on regression tasks.

Often we wish to transfer representational knowledge from one neural network to another. Examples include distilling a large network into a smaller one, transferring knowledge from one sensory modality to a second, or ensembling a collection of models into a single estimator. Knowledge distillation, the standard approa…

2019-10-23abs ↗pdf ↗

This paper improves speech recognition by distilling knowledge from acoustic models.

problem Improving speech recognition accuracy using ensemble models.
method Proposes multi-teacher distillation strategies for joint CTC-attention end-to-end ASR systems, integrating error rate metric for optimization.
result Reports state-of-the-art error rates on various datasets and languages.

We present a novel framework of knowledge distillation that is capable of learning powerful and efficient student models from ensemble teacher networks. Our approach addresses the inherent model capacity issue between teacher and student and aims to maximize benefit from teacher models during distillation by reducing t…

2019-11-29abs ↗pdf ↗

SPEQ improves quantized neural networks by stochastic precision sharing and cosine similarity loss.

problem Improving quantized deep neural networks for edge devices.
method SPEQ combines stochastic precision sharing and cosine similarity loss for knowledge distillation.
result SPEQ outperforms existing methods in various tasks.

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like to replace such cumbersome models with simpler models that perform equally well…

2015-10-08abs ↗pdf ↗

This paper connects RND, deep ensembles, and Bayesian inference, providing a unified theoretical perspective.

problem Uncertainty quantification in deep learning models.
method Analysis of Random Network Distillation (RND) within the neural tangent kernel framework.
result The uncertainty signal from RND is equivalent to the predictive variance of a deep ensemble and can be made to mirror the centered posterior predictive distribution of Bayesian inference.

New methods improve tree ensemble models by compressing them while maintaining accuracy.

problem Theoretical understanding and practical compression of tree ensembles like random forests and gradient boosting machines.
method Spectral perspective on tree ensembles, deriving minimax rates and developing compression schemes.
result Leading eigenfunctions/singular vectors capture dominant predictive directions, leading to smaller, competitive models.

Distilled models often fail to match teacher models, despite improving generalization.

problem The discrepancy between teacher and student predictive distributions remains large.
method Investigated the optimization difficulties and dataset details affecting student performance.
result Optimizing for matching the teacher does not always lead to better generalization.

In this study we examined the question of how error correction occurs in an ensemble of deep convolutional networks, trained for an important applied problem: segmentation of Electrocardiograms(ECG). We also explore the possibility of using the information about ensemble errors to evaluate a quality of data representat…

2018-12-26abs ↗pdf ↗

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always available. Recently proposed online variants use the aggregated intermediate pr…

2019-12-01abs ↗pdf ↗

A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions. Unfortunately, making predictions using a whole ensemble of models is cumbersome and may be too computationally expensive to allow deployment to…

2015-03-09abs ↗pdf ↗

UVU simplifies value uncertainty quantification in RL.

problem Estimating epistemic uncertainty in value functions for reinforcement learning.
method UVU uses squared prediction errors between an online learner and a fixed, randomly initialized target network, incorporating policy-conditional value uncertainty.
result UVU achieves equal performance to large ensembles on challenging offline RL settings, with computational savings.

Ensembles of deep neural networks significantly improve generalization accuracy. However, training neural network ensembles requires a large amount of computational resources and time. State-of-the-art approaches either train all networks from scratch leading to prohibitive training cost that allows only very small ens…

2018-09-12abs ↗pdf ↗

DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.

problem Diverse adversarial vulnerabilities for robust ensemble models.
method Isolates and diversifies adversarial vulnerabilities through distillation and training.
result Achieves higher robustness against transfer attacks compared to previous methods.

Compact Gaussian model approximates deep ensemble predictions.

problem Efficiently approximating deep ensemble models for image prediction.
method Sparse-structured multivariate Gaussian with Cholesky parameterization trained to match pre-trained ensemble outputs.
result Compact representation captures uncertainty and structured correlations explicitly.

FedZKT enables resource-constrained devices to participate in federated learning with heterogeneous models.

problem Inequality in resource allocation hinders participation from resource-constrained devices in federated learning.
method Zero-shot knowledge transfer through a server-assigned distillation process.
result FedZKT effectively transfers knowledge across heterogeneous on-device models without requiring comparable local training efforts.

Hybridizes physical and data-driven methods for predicting physicochemical properties.

problem Predicting physicochemical properties accurately using limited data.
method Distills physical method predictions into a prior model and combines with sparse experimental data using Bayesian inference.
result Significant improvements in predicting activity coefficients at infinite dilution compared to baselines and ensemble methods.

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.

Labels distilled from images improve model training efficiency and flexibility.

problem Creating synthetic labels for a small set of real images to train models effectively.
method Introduce a more robust and flexible meta-learning algorithm for distillation and an effective first-order strategy based on convex optimization layers.
result Label distillation leads to improved results and greater flexibility in neural architectures.

Dataset distillation is a method for reducing dataset sizes by learning a small number of synthetic samples containing all the information of a large dataset. This has several benefits like speeding up model training, reducing energy consumption, and reducing required storage space. Currently, each synthetic sample is …

2019-10-06abs ↗pdf ↗

Distillation affects some classes more than others, impacting fairness and bias.

problem Distillation affects some classes more than others, impacting fairness and bias.
method Examined class-wise accuracy and fairness metrics (DPD, EOD) on models trained with different datasets.
result Increasing the distillation temperature improves the distilled student model's fairness and individual fairness.