New method speeds up neural network training by preprocessing weight-data correlation.
problem Slow neural network training due to high time complexity.
method Stores weight-data correlation in a tree structure for quick detection of firing neurons.
result Achieves o(nmd) time per iteration with only O(nmd) preprocessing time. WICA improves ICA results with a new method.
problem Finding independent components in nonlinear data.
method New nonlinear ICA model (WICA) with efficient correlation coefficient verification.
result WICA yields better and more stable results than other algorithms.
Data clustering has received a lot of attention and numerous methods, algorithms and software packages are available. Among these techniques, parametric finite-mixture models play a central role due to their interesting mathematical properties and to the existence of maximum-likelihood estimators based on expectation-m…
As a consequence of the strong and usually violated conditional independence assumption (CIA) of naive Bayes (NB) classifier, the performance of NB becomes less and less favorable compared to sophisticated classifiers when the sample size increases. We learn from this phenomenon that when the size of the training data …
Independent Component Analysis (ICA) - one of the basic tools in data analysis - aims to find a coordinate system in which the components of the data are independent. In this paper we present Multiple-weighted Independent Component Analysis (MWeICA) algorithm, a new ICA method which is based on approximate diagonalizat…
Manipulating data, such as weighting data examples or augmenting with new instances, has been increasingly used to improve model training. Previous work has studied various rule- or learning-based approaches designed for specific types of data manipulation. In this work, we propose a new method that supports learning d…
Kernel-smoothed scores improve diffusion models by reducing memorization.
problem Diffusion models can memorize training data, leading to biased samples.
method Interpret empirical score as noisy version of true score, kernel-smoothed.
result Kernel-smoothing reduces variance and improves generalization.
Artificial neural network (ANN) is a very useful tool in solving learning problems. Boosting the performances of ANN can be mainly concluded from two aspects: optimizing the architecture of ANN and normalizing the raw data for ANN. In this paper, a novel method which improves the effects of ANN by preprocessing the raw…
Derives continuum model from discrete ε-graphs with connectivity functional.
problem Modeling diffusion in networks with varying connectivity.
method Energy-based continuum limit derivation, neural-network reconstruction of connectivity.
result Error between discrete and continuum energies is O(ε), valid even with fluctuations. Framework improves gradient estimation for faster training convergence.
problem Efficiently estimating noisy gradients in stochastic optimization.
method Dynamic adaptive importance sampling combining multiple distributions.
result Adaptively weighted multiple importance sampling yields superior gradient estimates.
Novel neural likelihood ratio estimation for negative data in particle physics.
problem Estimating likelihood ratios with negative probability densities and weights.
method Introducing a novel loss function and a new model architecture based on signed mixture models.
result Demonstrated improved estimation on a real-world example from particle physics.
Optimizes weights for better model performance in shifting data.
problem Improper importance weighting leads to poor model performance in data shifts.
method Interprets weights as a bias-variance trade-off and optimizes them simultaneously with model parameters.
result Optimizing weights significantly improves model generalization performance.
New method clusters hypergraphs using weighted random walks and Laplacians.
problem Clustering hypergraph data with edge-dependent weights.
method Random walks with edge-dependent vertex weights, constructing hypergraph Laplacians for clustering.
result Proposed methods outperform existing hypergraph clustering algorithms.
New method learns to weight unlabeled data in semi-supervised learning.
problem Equal weighting of all unlabeled data in semi-supervised learning.
method Adjust weights for each unlabeled example using influence function.
result Technique outperforms state-of-the-art methods on image and language classification tasks.
Retrieving the most similar objects in a large-scale database for a given query is a fundamental building block in many application domains, ranging from web searches, visual, cross media, and document retrievals. State-of-the-art approaches have mainly focused on capturing the underlying geometry of the data manifolds…
The paper classifies a space of generalized cusps and its moduli.
problem Classifying the moduli space of generalized cusps.
method Generalized cusp classification, representation theory, and geometric structures.
result The moduli space of generalized cusps is homeomorphic to a subspace of conjugacy classes of representations.
Unweighted matrix factorization can match or outperform weighted methods in recommender systems.
problem Improving recommendation performance with matrix factorization on implicit feedback data.
method Systematic study of various weighting schemes and matrix factorization algorithms.
result Training with unweighted data can perform comparably to, and sometimes outperform, training with weighted data.
Gradient descent with random weights in linear regression analyzed for various noise types.
problem Analyzing the impact of random noise on gradient descent in linear regression.
method Gradient descent with randomly weighted data points, various weighting distributions, geometric moment contraction.
result Characterization of implicit regularization and non-asymptotic convergence bounds.
A new method for efficient Gaussian process regression reduces complexity and improves scalability.
problem Efficient Gaussian process regression for large datasets.
method Learnable coreset-based variational inference for Gaussian processes.
result CVGP reduces the dimensionality of the variational parameter search space to linear complexity.
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.
Deep Neural Networks (DNNs) are applied in a wide range of usecases. There is an increased demand for deploying DNNs on devices that do not have abundant resources such as memory and computation units. Recently, network compression through a variety of techniques such as pruning and quantization have been proposed to r…
This paper recovers input data from transformer models using attention weights.
problem Recovering input data from transformer models for security and privacy concerns.
method Introducing an algorithm to minimize the loss function between expected and actual outputs of transformers.
result The algorithm successfully recovers input data from attention weights and outputs of transformers.
Under what conditions is an edge present in a social network at time t likely to decay or persist by some future time t + Delta(t)? Previous research addressing this issue suggests that the network range of the people involved in the edge, the extent to which the edge is embedded in a surrounding structure, and the age…
We present a new approach to the problems of evaluating and learning personalized decision policies from observational data of past contexts, decisions, and outcomes. Only the outcome of the enacted decision is available and the historical policy is unknown. These problems arise in personalized medicine using electroni…
Learning policies on data synthesized by models can in principle quench the thirst of reinforcement learning algorithms for large amounts of real experience, which is often costly to acquire. However, simulating plausible experience de novo is a hard problem for many complex environments, often resulting in biases for …
This thesis explores fast algorithms for large matrices and data augmentation to improve model efficiency.
problem Efficient handling of large models and data in scientific computing and machine learning.
method Randomized low-rank decomposition algorithms and data augmentation techniques.
result Improved sample efficiency and generalization of machine learning models.
This work connects neural network training to convex optimization via the NTK.
problem Understanding and optimizing neural network training via convex programs.
method Interpreting gated ReLU network as MKL, showing NTK equivalence, and improving weights.
result The NTK cannot perform better than the optimal MKL kernel on the training set.
This work optimizes induced correlation in joint graph embeddings.
problem Optimizing correlation across embedded networks in joint graph embeddings.
method Developed corr2Omni algorithm to estimate optimal Omnibus weights.
result corr2Omni algorithm improves inference fidelity compared to classical Omnibus construction.
In this paper we use wavelet concepts to show that correlation coefficient between two financial data's is not constant but varies with scale from high correlation value to strongly anti-correlation value This studies is important because correlation coefficient is used to quantify degree of independence between two va…
We analyze the daily stock data of the Nasdaq Composite index in the 22-year period 1992-2013 and identify market states as clusters of correlation matrices with similar correlation structures. We investigate the stability of the correlation structure of each state by estimating the statistical fluctuations of correlat…
The study uses DCC for financial market analysis, revealing hidden correlations.
problem Identifying hidden nonlinear correlations in financial markets.
method Agglomerative hierarchical clustering with distance correlation coefficient.
result DCC reveals more information than Pearson correlation for financial data.
This study uses local Gaussian correlation to analyze stock return tails, revealing more sensitive network properties.
problem Misleading results from Pearson correlation in financial networks.
method Local Gaussian correlation coefficient for capturing nonlinear dependence and heavy-tailed distributions.
result Local Gaussian correlation network among negative tails is more sensitive to stock market risks.
Polynomial time algorithm matches correlated Gaussian matrices without vanishing correlation.
problem Matching vertices in two correlated Erdős-Rényi graphs.
method Iterative matching algorithm for correlated Gaussian Wigner matrices.
result First polynomial time algorithm for graph matching with arbitrarily small constant correlation.
This paper treats the problem of screening for variables with high correlations in high dimensional data in which there can be many fewer samples than variables. We focus on threshold-based correlation screening methods for three related applications: screening for variables with large correlations within a single trea…
This paper introduces anti-correlation networks to study China's stock market.
problem Previous studies ignored anti-correlation in financial networks.
method Constructed weighted temporal anti-correlation and positive correlation networks.
result Unveiled differences in topological measurements between anti-correlation and positive correlation networks.
The study shows how trade uncertainty affects stock-bond correlations over time.
problem Impact of trade policy uncertainty on stock-bond correlations.
method Daily data analysis using GARCH-based models (CCC, STCC, DCC) with TPU and political dummy variables.
result Time-varying correlation models better capture the dynamics of stock-bond correlations than constant models.
Infinite CNNs lose spatial correlations, but can be restored by correlated weights.
problem Infinite CNNs lose spatial correlations, which are crucial for their performance.
method Introduced correlated weights to restore spatial correlations in infinite CNNs.
result Optimal performance is achieved with a moderate level of weight correlation.
We discuss some methods to quantitatively investigate the properties of correlation matrices. Correlation matrices play an important role in portfolio optimization and in several other quantitative descriptions of asset price dynamics in financial markets. Specifically, we discuss how to define and obtain hierarchical …
This research examines rare spurious correlations in neural networks and their impact on accuracy and privacy.
problem Rare spurious correlations in neural networks and their privacy risks.
method Introducing spurious patterns correlated with a fixed class to a few training examples, analyzing ℓ2 regularization and Gaussian noise. result Rare spurious correlations can significantly impact neural network accuracy and privacy, and specific mitigation methods can be effective.
The study reveals how synaptic correlations promote dimension reduction in neural networks.
problem Understanding how synaptic correlations affect neural correlations and dimension reduction in deep neural networks.
method A simplified model of dimension reduction considering pairwise correlations among synapses, using mathematical self-consistency for both binary and continuous synapses.
result Weakly-correlated synapses encourage dimension reduction compared to orthogonal synapses, and they also slow down the decorrelation process.
Proposes PSCCA for estimating correlations and canonical correlations in sparse count data.
problem Estimating correlations and canonical correlations in sparse count data from next-generation sequencing.
method Probabilistic approach for sparse count data sets (PSCCA).
result PSCCA outperforms other methods in estimating true correlations and canonical correlations at the natural parameter level.
Study examines NFT market dynamics using correlation and noise analysis.
problem Understanding correlations and noise in NFT market.
method Used detrended correlation coefficient and correlation matrix analysis.
result Correlation strength in NFT market is lower than in cryptocurrency markets.
Polynomial-time algorithm matches correlated random graphs with non-vanishing correlation.
problem Matching correlated random graphs with non-vanishing edge correlation.
method Iterative algorithm for polynomial-time recovery of latent matching.
result Algorithm succeeds in recovering latent matching as long as edge correlation is non-vanishing.
Proposes a multi-view VAE for imputing missing data from correlated sources.
problem Imputing missing data from multi-view sources with latent space correlation.
method Enforces a joint prior with latent space correlation between VAEs trained on each view.
result More strongly correlated latent spaces are uncovered, enabling effective imputation.
Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of correlated variability, we implement and evaluate correlated noise models in deep convolu…
Enhances community detection in correlated networks with node attributes.
problem Community detection in multiple networks with correlated node attributes and edges.
method Introduced the correlated Contextual Stochastic Block Model (CSBM), developed a two-step matching procedure.
result Algorithm recovers exact node correspondence, enabling enhanced community detection.
New method detects intrinsic cross-correlations in non-stationary time series affected by common factors.
problem Bias in cross-correlation analysis due to common external factors.
method Multifractal temporally weighted detrended partial cross-correlation analysis (MF-TWDPCCA).
result MF-TWDPCCA accurately detects intrinsic cross-correlations between non-stationary time series.
Develops correlation number for specific potentials and Hitchin representations.
problem Analyzing correlation numbers for potentials with entropy gaps and Hitchin representations.
method Defines a correlation number for pairs of cusped Hitchin representations and explores its connection to the Manhattan curve.
result Establishes a connection between the correlation number and the Manhattan curve, revealing rigidity properties.