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.
Spectral dimensionality reduction algorithms are widely used in numerous domains, including for recognition, segmentation, tracking and visualization. However, despite their popularity, these algorithms suffer from a major limitation known as the "repeated Eigen-directions" phenomenon. That is, many of the embedding co…
This work compares data reduction criteria for online Gaussian Processes.
problem The computational complexity of Gaussian Processes limits their applicability to small datasets and streaming scenarios.
method Unified comparison of several data reduction criteria, analyzing computational complexity and reduction behavior.
result Practical guidelines for choosing a suitable data reduction criterion for online Gaussian Processes.
This paper tackles the reduction of redundant repeating generation that is often observed in RNN-based encoder-decoder models. Our basic idea is to jointly estimate the upper-bound frequency of each target vocabulary in the encoder and control the output words based on the estimation in the decoder. Our method shows si…
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.
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.
The paper simplifies symmetries in complex geometric structures.
problem Redundancy in conditions for symmetry reduction in polysymplectic and polycosymplectic structures.
method Exploring and proving necessary and sufficient conditions for polycosymplectic reduction.
result A one-to-one relationship between polycosymplectic reduction and the reduction of a larger polysymplectic manifold.
This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective. This algorithm can remove substantial non-zero weighting parameters (redundant neural channels) of a network by considering its dynamic behavior, which traditional model-compaction te…
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.
FactorMiner discovers financial alpha factors with low redundancy.
problem Finding novel financial alpha factors in a vast search space.
method Modular Skill Architecture and Experience Memory to distill and guide exploration.
result FactorMiner constructs a diverse library of high-quality factors with competitive performance.
New method for evaluating LLMs reduces bias in open-ended evaluations.
problem Bias in Elo-based ratings of LLMs due to data redundancies.
method Proposes evaluation as a 3-player game and introduces novel solution concepts.
result Novel method leads to more robust and intuitive ratings.
Signed pairwise interactions conflate uniqueness, redundancy, and synergy
problem Signed pairwise interactions conflate uniqueness, redundancy, and synergy
method Stochastic Hi-Fi
result Stochastic Hi-Fi recovers structure missed by scalar baselines
The sophisticated structure of Convolutional Neural Network (CNN) allows for outstanding performance, but at the cost of intensive computation. As significant redundancies inevitably present in such a structure, many works have been proposed to prune the convolutional filters for computation cost reduction. Although ex…
Cell-based NAS search spaces are redundant and lack novelty.
problem Redundancy and lack of novelty in cell-based neural architecture search.
method Empirical analysis of architectures from popular cell-based search spaces.
result Randomly sampled architectures can match or outperform state-of-the-art results.
With the advent of Big Data era, data reduction methods are highly demanded given its ability to simplify huge data, and ease complex learning processes. Concretely, algorithms that are able to filter relevant dimensions from a set of millions are of huge importance. Although effective, these techniques suffer from the…
Redundancy in AI perception systems doesn't guarantee independent error occurrences.
problem Lack of direct statistical evidence of super-human automated driving performance.
method Investigated the effectiveness of redundancy in neural networks for independent error occurrences.
result Errors in neural networks for computer vision tasks are correlated, not independent.
We develop a novel method, called PoWER-BERT, for improving the inference time of the popular BERT model, while maintaining the accuracy. It works by: a) exploiting redundancy pertaining to word-vectors (intermediate encoder outputs) and eliminating the redundant vectors. b) determining which word-vectors to eliminate …
Experimental life sciences like biology or chemistry have seen in the recent decades an explosion of the data available from experiments. Laboratory instruments become more and more complex and report hundreds or thousands measurements for a single experiment and therefore the statistical methods face challenging tasks…
We give a simple and effective two stage algorithm for approximating a point cloud S⊂Rm by a simplicial complex K. The first stage is an iterative fitting procedure that generalizes k-means clustering, while the second stage involves deleting redundant simplices. A form of dimension reduct…
Binarized Neural Network (BNN) removes bitwidth redundancy in classical CNN by using a single bit (-1/+1) for network parameters and intermediate representations, which has greatly reduced the off-chip data transfer and storage overhead. However, a large amount of computation redundancy still exists in BNN inference. B…
In this paper we propose the macroblock scaling (MBS) algorithm, which can be applied to various CNN architectures to reduce their model size. MBS adaptively reduces each CNN macroblock depending on its information redundancy measured by our proposed effective flops. Empirical studies conducted with ImageNet and CIFAR-…
Channel Pruning, widely used for accelerating Convolutional Neural Networks, is an NP-hard problem due to the inter-layer dependency of channel redundancy. Existing methods generally ignored the above dependency for computation simplicity. To solve the problem, under the Bayesian framework, we here propose a layer-wise…
Funnel-Transformer reduces computation by compressing sequence data.
problem Redundant token-level representations in language processing.
method Gradually compresses sequence of hidden states to a shorter one.
result Funnel-Transformer outperforms standard Transformer with fewer FLOPs.
Paper reduces movement primitive dimensionality in parameter space.
problem High dimensionality of movement primitives makes policy optimization expensive.
method Investigates dimensionality reduction in parameter space, identifying principal movements.
result Dimensionality reduction in parameter space is more effective than in configuration space.
New method disentangles high-order effects in feature importance.
problem Quantifying cooperative effects in feature importance.
method Adaptive Leave One Covariate Out (LOCO) method to decompose LOCO into two-body and higher-order components.
result Decomposes LOCO into two-body and higher-order components, highlighting synergistic and redundant effects.
Williams and Beer (2010) proposed a nonnegative mutual information decomposition, based on the construction of redundancy lattices, which allows separating the information that a set of variables contains about a target variable into nonnegative components interpretable as the unique information of some variables not p…
CurvSSL improves SSL by aligning local manifold curvature.
problem Improving self-supervised learning by capturing local manifold geometry.
method CurvSSL augments Barlow Twins with a curvature-based regularizer to align and decorrelate embeddings across augmentations.
result Curvature-regularized SSL yields competitive or improved linear evaluation performance.
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.
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.
This paper introduces a new unsupervised method for dimensionality reduction via regression (DRR). The algorithm belongs to the family of invertible transforms that generalize Principal Component Analysis (PCA) by using curvilinear instead of linear features. DRR identifies the nonlinear features through multivariate r…
Hippo optimizes deep learning hyper-parameters by reducing redundant trials.
problem Redundant hyper-parameter trials in hyper-parameter optimization.
method Hippo breaks down hyper-parameter sequences into stages and executes them in a tree structure.
result Hippo reduces GPU-hours and training time significantly compared to existing methods.
Convolutional neural networks (CNN) are generally designed with a heuristic initialization of network architecture and trained for a certain task. This often leads to overparametrization after learning and induces redundancy in the information flow paths within the network. This robustness and reliability is at the inc…
PruneNet efficiently prunes channels in deep networks, improving accuracy and performance.
problem Improving deep neural network performance and efficiency through channel pruning.
method PruneNet uses a computationally light-weight optimization step to identify and prune channels based on layer redundancy.
result Pruned ResNet models achieve higher accuracy and better performance than non-pruned models.
New algorithm estimates treatment effects for more efficient contextual bandits.
problem Contextual bandits struggle with action-independent reward redundancies.
method Reduces contextual bandits to heterogeneous treatment effect estimation.
result Heterogeneous treatment effect estimation leads to more efficient model estimation.
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.
New method reduces PDE model parameters by 30% with sparsity.
problem Redundant parameters in neural network projections.
method Bregman iterations for sparsity, POD compression, bias propagation.
result 30% fewer parameters with similar accuracy.
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.
For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. "Dirty" non-curated data gives rise to categorical variables with a very high cardinality but redundancy: several categories reflect the same ent…
RIn-Close_CVC is an efficient (take polynomial time per bicluster), complete (find all maximal biclusters), correct (all biclusters attend the user-defined level of consistency) and non-redundant (all the obtained biclusters are maximal and the same bicluster is not enumerated more than once) enumerative algorithm for …
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.
Redundancy in deep neural network (DNN) models has always been one of their most intriguing and important properties. DNNs have been shown to overparameterize, or extract a lot of redundant features. In this work, we explore the impact of size (both width and depth), activation function, and weight initialization on th…
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. Bayesian sparsification reduces deep neural network complexity.
problem Complexity of deep neural networks limits their performance.
method Combines Bayesian shrinkage priors with stochastic variational inference.
result Bayesian model reduction (BMR) is a more efficient alternative for pruning model weights.
This work proposes a collaborative multi-head attention layer to reduce model size without sacrificing accuracy.
problem Over-parameterization in transformer models trained with large datasets.
method Proposes a collaborative multi-head attention layer that shares key/query projections.
result Reduction in model size by 4 for same accuracy and speed.
New method reduces state redundancy in HSMM for driving patterns.
problem Overestimation of states in HSMM models.
method Robust HDP-HSMM (rHDP-HSMM) method to reduce redundant states.
result Improved consistency and accurate inference of driving maneuvers.
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.
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.