This paper finds a new way to compress CNN weights, improving on pruning and quantization.
problem Improving performance and storage efficiency of CNNs.
method Identifying and exploiting repeated patterns in CNN weight tensors, using Huffman coding and block sparse matrix formats.
result Achieved compaction ratios of 1.4x to 3.1x in addition to pruning and quantization.
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…
Efficient algorithm removes redundant nodes and obsolete samples in machine learning.
problem Pruning redundant nodes and removing obsolete training samples in machine learning.
method Deduced decremented learning algorithms from incremental learning algorithms, using inverse Cholesterol factor and unitary transformation.
result Proposed decremented learning algorithms efficiently prune redundant nodes and remove obsolete training samples.
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 introduces the Partition Tree Weighting technique, an efficient meta-algorithm for piecewise stationary sources. The technique works by performing Bayesian model averaging over a large class of possible partitions of the data into locally stationary segments. It uses a prior, closely related to the Context T…
Proposes a novel network for CTR prediction by learning modality-specific and modality-invariant representations.
problem Learning good representation of items from multimodal features in E-commerce is challenging due to redundant information across modalities.
method Introduces a Multimodal Adversarial Representation Network (MARN) that calculates modality-specific weights and learns modality-invariant representations.
result Consistently achieves remarkable improvements over state-of-the-art methods in CTR prediction.
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.
Gradient descent trains shallow neural networks to approximate functions in 1D.
problem Approximating functions in 1D with shallow neural networks trained by gradient descent.
method Gradient descent optimization of non-convex weight space for finite width networks in 1D.
result Gradient descent can approximate functions in 1D with a minimal number of weights, balancing practical performance and theoretical capabilities.
We introduce a new parameterization method for deep learning layers using spectral tensor train decomposition.
problem Efficiency and stability in deep learning models with weight matrix compression.
method Spectral Tensor Train Parameterization (STTP) of weight matrices.
result Improved compression and training stability in neural networks.
PAC-Bayesian bounds improve understanding of K-NN classifier performance.
problem Improving the understanding of K-NN classifier's generalization error.
method PAC-Bayesian analysis applied to K-NN classifier in kernel space.
result PAC-Bayesian bounds provide a function of the number of redundant training examples.
FlipOut prunes neural networks by flipping weights' signs, achieving high sparsity.
problem Redundant weights in neural networks increase training time and resource usage.
method Uses sign flips during training to determine weight saliency for pruning.
result Competitive with existing methods, achieving state-of-the-art performance for high sparsity.
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…
Bayesian model averaging under predictor redundancy
problem Reporting Bayesian model averaging posterior without changing the Bayesian target
method Using hard or soft regions of support space
result Region reports often give shorter and clearer summaries while preserving the main posterior information
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…
Transformer models waste resources on long-context tasks.
problem Redundant attention computations in Transformer models for long-context tasks.
method Reformulate sequence modeling as supervised learning, analyze attention sparsity, formulate attention optimization as linear coding problem, propose Dynamic Group Attention.
result DGA reduces computational costs while maintaining performance.
Compressing convolutional neural networks (CNNs) is essential for transferring the success of CNNs to a wide variety of applications to mobile devices. In contrast to directly recognizing subtle weights or filters as redundant in a given CNN, this paper presents an evolutionary method to automatically eliminate redunda…
We demonstrate that there is significant redundancy in the parameterization of several deep learning models. Given only a few weight values for each feature it is possible to accurately predict the remaining values. Moreover, we show that not only can the parameter values be predicted, but many of them need not be lear…
This paper challenges the conventional wisdom of trend-following by showing that the medium-term horizon adds little value once short- and long-term components are included.
problem The conventional wisdom that more horizons improve diversification and performance is challenged.
method A Bayesian optimization framework reallocates exposure dynamically across horizons, optimizing horizon-level weights at the asset level and applying sparsity and turnover control for dynamic allocation across assets.
result The medium-term horizon contributes little incremental performance or diversification once short- and long-term components are included.
A federated method for feature selection in multi-label data.
problem Feature selection in multi-label data for distributed and federated environments.
method Semi-Supervised Federated Multi-Label Feature Selection (SSFMLFS) using fuzzy information measures.
result SSFMLFS outperforms other methods in feature selection for multi-label data in federated settings.
Enhances financial time series forecasting with a multi-period learning framework.
problem Accurate financial time series forecasting requires considering both short-term and long-term trends.
method Proposes a Multi-period Learning Framework (MLF) with three modules: Inter-period Redundancy Filtering, Learnable Weighted-average Integration, and Multi-period self-Adaptive Patching.
result Improves financial time series forecasting accuracy and efficiency.
Network quantization is one of the most hardware friendly techniques to enable the deployment of convolutional neural networks (CNNs) on low-power mobile devices. Recent network quantization techniques quantize each weight kernel in a convolutional layer independently for higher inference accuracy, since the weight ker…
Improved Bayesian neural network inference by selectively removing redundant modes.
problem Redundant modes in Bayesian neural network posteriors complicate approximate inference.
method Structured partial stochasticity and deterministic subset selection of weights.
result Improved performance of approximate inference schemes with simplified posterior distribution.
Novel approach reduces DNN redundancy and enhances computational efficiency.
problem Redundant parameters in large-scale DNNs pose hardware deployment challenges.
method WGSEF regularization technique for structured sparsity.
result Reduces redundancy and enhances computational efficiency.
TIME network simplifies complex physical processes with interpretable models.
problem Challenges in learning coupled dynamic processes from multiple observations.
method Fully convolutional architecture capturing invariant domain structure.
result Robust and transparent in capturing process kernels and anomalies.
Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compression with two main approaches. Weight pruning leverages the redundancy i…
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…
The study reveals flaws in pruning criteria and proposes a new assumption for better filter selection.
problem Flaws in existing pruning criteria for CNNs.
method Empirical experiments and Convolutional Weight Distribution Assumption.
result The Convolutional Weight Distribution Assumption improves filter selection in pruning.
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.
Due to the insufficient measurements in the distribution system state estimation (DSSE), full observability and redundant measurements are difficult to achieve without using the pseudo measurements. The matrix completion state estimation (MCSE) combines the matrix completion and power system model to estimate voltage b…
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.
New method reconstructs stable sentiment signals from sparse news data.
problem Transforming raw news sentiment outputs into reliable temporal series.
method Modular three-stage pipeline: aggregation, gap filling, and smoothing.
result Three-week lead-lag pattern between reconstructed sentiment and stock prices.
This work explores how overparametrization and priors affect Bayesian neural network posteriors.
problem Symmetries, non-identifiabilities, and weight-space priors fragment and inflate BNN posteriors.
method We study the interplay between overparametrization and priors in BNN posteriors, deriving key phenomena and validating through experiments.
result Overparametrization induces structured, prior-aligned weight posterior distributions.
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…
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.
MPWTSVM improves multi-view learning by reducing redundancy and enhancing accuracy.
problem Improving multi-view learning models for better accuracy and efficiency.
method Proposes MPWTSVM, which combines WLTSVM's strengths with multi-view learning principles.
result Demonstrates better accuracy and efficiency compared to existing multi-view classification 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…
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.
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.
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.
Importance weighted variational inference (Burda et al., 2015) uses multiple i.i.d. samples to have a tighter variational lower bound. We believe a joint proposal has the potential of reducing the number of redundant samples, and introduce a hierarchical structure to induce correlation. The hope is that the proposals w…
This paper establishes rates of universal approximation for the shallow neural tangent kernel (NTK): network weights are only allowed microscopic changes from random initialization, which entails that activations are mostly unchanged, and the network is nearly equivalent to its linearization. Concretely, the paper has …
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.
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.
We present and test a sequential learning algorithm for the short-term prediction of human mobility. This novel approach pairs the Exponential Weights forecaster with a very large ensemble of experts. The experts are individual sequence prediction algorithms constructed from the mobility traces of 10 million roaming mo…