PoWER-BERT speeds up BERT inference by eliminating redundant word-vectors.
problem Improving BERT inference speed without sacrificing accuracy.
method Eliminating redundant word-vectors using a self-attention-based significance measure and learning the number of vectors to eliminate.
result Up to 4.5x reduction in inference time with <1% loss in accuracy on GLUE benchmark.
Transformers reduce redundancy by focusing on invariant relational quantities.
problem Substantial internal redundancy in Transformer models due to coordinate-dependent representations and continuous symmetries.
method Reformulate representations, attention mechanisms, and optimization dynamics in terms of invariant relational quantities, eliminating redundant degrees of freedom by construction.
result Architectures that operate directly on relational structures, providing a principled geometric framework for reducing parameter redundancy and analyzing optimization.
HAGs eliminate redundant computations in GNNs, improving training efficiency.
problem Redundant computations in GNNs leading to inefficiencies.
method Hierarchically Aggregated computation Graphs (HAGs) to manage and eliminate redundant computations.
result Significant improvement in training efficiency (up to 2.8x) with HAGs.
AMBER method selects features efficiently using autoencoders and model-based elimination.
problem Efficiently selecting relevant features for classification.
method Greedy backward elimination using a ranker model and autoencoders.
result AMBER outperforms other feature selection methods in classification accuracy.
Paper compresses deep neural networks by eliminating redundant neurons.
problem Challenges in deploying deep learning models due to high parameter count.
method Exploits non-linear redundancy to compress neural networks without loss.
result Reduces network size by up to 99% with minimal performance loss.
BELIEF method efficiently selects features from Big Data sets.
problem Feature selection for large datasets in Big Data.
method Distributed feature weighting algorithm using redundancy elimination.
result BELIEF method ranks millions of features in parallel efficiently.
Two new Hie-TAN and Hie-TAN-Lite algorithms improve TAN for hierarchical feature spaces.
problem Learning dependencies in hierarchical feature spaces.
method Exploits hierarchical parent-child relationships as constraints to learn a dependency tree.
result Hie-TAN-Lite outperforms Hie-TAN and other methods in predictive accuracy.
AE-DQN learns to eliminate sub-optimal actions in complex RL environments.
problem Challenges in RL with many actions, especially redundancy.
method Combines DQN with AEN that predicts invalid actions.
result Significant speedup and robustness in games with many actions.
Feature selection has attracted significant attention in data mining and machine learning in the past decades. Many existing feature selection methods eliminate redundancy by measuring pairwise inter-correlation of features, whereas the complementariness of features and higher inter-correlation among more than two feat…
Evolutionary method reduces CNN complexity for mobile devices.
problem Efficiently compressing CNNs for mobile devices.
method Evolutionary algorithm to identify and remove redundant convolution filters.
result Generates an extremely compact CNN with improved compression and speed-up ratios.
DRACO improves robustness in distributed training by using redundant gradients.
problem Byzantine failures and adversarial compute nodes corrupting model training.
method DRACO uses redundant gradients to eliminate adversarial updates, leveraging coding theory.
result DRACO provides problem-independent robustness guarantees and is significantly faster than median-based approaches.
mRMR method selects relevant features for marketing models without redundancy.
problem Selecting relevant features from large feature spaces in machine learning.
method Extends mRMR framework with non-linear redundancy and model-based relevance measures.
result Implemented mRMR method in production for Uber's marketing machine learning platform.
Improves model predictability by mixing forecasts and orthogonalizing models.
problem Redundant models contaminate model space and degrade predictive performance.
method Principal Component Analysis for model orthogonalization in Bayesian forecast mixing.
result Better prediction accuracy and excellent uncertainty quantification.
A2 Learning reduces redundant examples in AL for NLP tasks.
problem Redundant examples in AL strategies waste annotation effort.
method A2 Learning actively adapts to deep learning models to eliminate redundant examples.
result A2 Learning reduces data requirements by 3-25% on NLP tasks.
Study reduces redundant information in multi-modal datasets.
problem Redundant information increases data size and costs.
method Multimodal framework using entropy, mutual info, Lasso, SHAP, PCA, topic modeling.
result Significant feature space can be pruned with minimal loss in performance.
The leaderboard in machine learning competitions is a tool to show the performance of various participants and to compare them. However, the leaderboard quickly becomes no longer accurate, due to hack or overfitting. This article gives two pieces of advice to prevent easy hack or overfitting. By following these advice,…
SAE-FiRE extracts key financial info from long documents, improving earnings surprise predictions.
problem Predicting earnings surprises from long, redundant financial documents.
method Sparse Autoencoder feature selection to filter out noise and identify key dimensions.
result SAE-FiRE significantly outperforms baseline approaches in financial datasets.
A new approach of solving the ill-conditioned inverse problem for analytical continuation is proposed. The root of the problem lies in the fact that even tiny noise of imaginary-time input data has a serious impact on the inferred real-frequency spectra. By means of a modern regularization technique, we eliminate redun…
New method quantifies multivariate redundancy using maximum entropy decompositions.
problem Elusive multivariate measures of redundancy that comply with nonnegativity and axioms.
method Maximum entropy framework, rooted tree-based decompositions of mutual information.
result Quantifies different multivariate redundancy contributions.
Greedy selection finds smaller, more accurate subnetworks.
problem Finding smaller, accurate subnetworks in large neural networks.
method Greedy forward selection starting from an empty network.
result Theoretical guarantee of finding subnetworks with lower loss.
Optimization-based pruning eliminates backpropagation for large language models.
problem Suboptimal pruning performance due to heuristic metrics.
method Optimization of Bernoulli distribution to learn pruning masks without backpropagation.
result Efficient pruning of large language models with improved performance.
A genetic algorithm with community detection improves feature selection accuracy.
problem Feature selection in high-dimensional datasets.
method Community detection in genetic algorithm for feature selection.
result The new approach yields improved classification accuracy.
The paper introduces a method to explain redundancy in deep CNNs using unit impulse response.
problem Redundancy in deep CNNs leads to unnecessary computations and increased cost.
method Empirical demonstration and unit impulse response analysis to identify and quantify redundancy across layers and depth.
result Identifies and quantifies redundancy in deep CNNs, providing better insights into their internal dynamics.
Redundancy improves learning stability and generalization in structured systems.
problem Understanding redundancy in structured systems for learning and generalization.
method Developed a theoretical framework that redefines redundancy as a geometric principle unifying various measures.
result Redundancy balances structure and coupling, leading to optimal stability and generalization.
New method quantifies redundant information using information bottleneck.
problem Quantifying redundant information among multiple sources.
method Formulated as an information bottleneck problem, termed redundancy bottleneck.
result Extracts information that best predicts the target without revealing source identity.
Factorial hidden Markov models (FHMMs) are powerful tools of modeling sequential data. Learning FHMMs yields a challenging simultaneous model selection issue, i.e., selecting the number of multiple Markov chains and the dimensionality of each chain. Our main contribution is to address this model selection issue by exte…
Finsler geometry connects to higher-spin fields and curved-space Fronsdal equations.
problem Eliminating non-transverse modes in Finsler dynamics for higher spins.
method Parameterizing Finsler geometry in terms of symmetric tensors, analyzing linear and nonlinear terms, and examining gauge transformations.
result Finsler dynamics leads to the curved-space Fronsdal equation for all spins, plus a Stueckelberg-like coupling.
ZeRO optimizes memory for training large models, scaling to trillions of parameters.
problem Training models with billions to trillions of parameters is challenging due to limited device memory.
method ZeRO eliminates memory redundancies in data- and model-parallel training, scaling model size proportional to the number of devices.
result ZeRO trains models of up to 13B parameters without model parallelism, achieving super-linear speedup and throughput of 15 Petaflops.
Study shows DNNs often extract redundant features, influenced by network size and activation function.
problem Redundancy in deep neural network features.
method Hierarchical clustering of features based on cosine distances, varying network sizes and activation functions.
result Network size and activation function are key factors in DNN redundancy.
Paper proposes redundancy-free features for zero-shot object recognition.
problem Redundant visual features degrade zero-shot object recognition.
method Project original features into a new, statistically independent space.
result RFF-GZSL achieves competitive results on benchmark datasets.
This work explains scaling laws as redundancy laws in deep learning.
problem The mathematical origins of scaling laws in deep learning models remain unclear.
method Kernel regression and analysis of data covariance spectra.
result Scaling laws can be explained as redundancy laws, revealing the learning curve's slope depends on data redundancy.
Study on neural networks to identify redundancy issues in safe machine learning.
problem Identifying redundancy in neural network architectures for safe machine learning.
method Experiments with MNIST database using neural network classifiers.
result Underlines difficulties in using neural network classifiers for safe systems.
PenduMAV is a 6-input omnidirectional MAV without internal forces.
problem Designing a MAV without internal forces and structural costs.
method Multibody dynamics derivation, SE(3) control, Lyapunov analysis, Gazebo simulations.
result Asymptotic stabilization of the closed-loop system under parametric uncertainty and actuator noise.
Study finds 10% redundant images in image classification datasets.
problem Redundancy in large image classification datasets.
method Analysis of CIFAR-10 and ImageNet datasets to identify redundant images.
result 10% of images are redundant and can be removed without significant loss of performance.
A new method for efficient CNN compression by incrementally assigning regularization factors to weights.
problem Efficiently compressing ConvNets while maintaining performance.
method IncReg: Incremental Regularization for Parameter Pruning.
result IncReg achieves comparable or better results than state-of-the-art methods.
Clustering helps reduce spatial data size by identifying redundant points.
problem Too much spatial data makes it hard to answer research questions.
method Density-based clustering to compress data into representative features.
result Reduces spatial data set size by identifying and removing redundant points.
We simplify SSL by approximating redundant structural components with low-rank factorization.
problem Improving self-supervised learning performance with limited labeled data.
method Low-rank approximation of structural redundancy, introducing ε_s to measure approximation quality.
result The proposed method enhances SSL performance, as shown by theoretical and experimental validations.
This paper introduces a new measure to identify model redundancy in compressed CNNs.
problem Identifying remaining model redundancy in compressed CNNs.
method Developed a statistical formulation of CNNs and compressed CNNs via tensor decomposition, revealing discrepancies in sample complexity and model redundancy.
result Introduced a new model redundancy measure, the K/R ratio, for compressed CNNs. This paper explores how optimizing data access and reducing redundancy can improve machine learning algorithm performance.
problem Performance issues in machine learning algorithms due to data locality and redundancy.
method Analysis of data access patterns and computational redundancy in machine learning algorithms, identifying opportunities for reuse and experimentation.
result Initial indicative results show potential for improving performance through data access optimization and reuse of computation results.
Paper tackles action selection in deep RL, proposing a data-driven approach.
problem High-dimensional action selection in deep RL environments.
method Data-driven approach with knockoff sampling for minimal sufficient actions.
result Method surpasses alternative techniques in performance and rewards.
Optimized GPRNN reduces model complexity and overfitting, improving performance.
problem Overfitting in neural networks and high model complexity.
method Gaussian Process Regression - Neural Network hybrid with optimized redundant coordinates.
result Optimized GPRNN achieves lower test set error with fewer terms/neurons.
One of Powell's generators is not necessary.
problem Unresolved conjecture about generating Goeritz group.
method Short argument showing redundancy of one generator.
result One of Powell's generators is a consequence of others.
The study analyzes optimization trajectories in neural networks to reveal redundancy and redundancy-reducing strategies.
problem Understanding the directional structure and redundancy in neural network optimization.
method Introducing natural notions of complexity for optimization trajectories and analyzing their directional nature.
result Training only scalar batchnorm parameters can match the performance of training the entire network, indicating potential for hybrid optimization schemes.
This work introduces RISE to explain LLMs more reliably by distinguishing essential context.
problem Identifying which context elements influence LLM outputs reliably.
method RISE (Redundancy-Insensitive Scoring of Explanation) method.
result RISE provides more robust explanations than traditional methods.
This work identifies redundant tests in conditional-independence-based discovery that can improve graphical model accuracy.
problem Reliability and sensitivity of conditional-independence-based discovery algorithms.
method Analysis of redundant tests and their impact on error detection and correction.
result Redundant tests can improve graphical model accuracy but not all are beneficial.
Contrastive learning works well with redundant data views.
problem Improving unsupervised learning with redundant data views.
method Theoretical analysis of contrastive learning in a multi-view setting.
result Linear functions of learned representations are nearly optimal on prediction tasks when views are redundant.
DETOX improves distributed training resilience with redundancy and robust aggregation.
problem Byzantine node failures in distributed training.
method Combines redundancy and robust aggregation methods.
result Substantial increase in robustness with nearly linear runtime.
A novel method for feature selection using a reparameterized logitNormal distribution.
problem Feature selection for reconstruction in high-dimensional data.
method Introducing a reparameterization of the logitNormal distribution to address differentiability and covariance issues.
result The method provides an effective exploration scheme and efficient feature selection for reconstruction.