Adaptive correlated MC improves sequence generation stability.
problem High gradient variance in reinforcement learning for sequence generation.
method Adapts policy gradient estimator using correlated Monte Carlo rollouts.
result Reduces gradient variance and improves model performance.
A new natural gradient accounts for correlated variational parameters in variational inference.
problem Traditional natural gradients fail to correct for correlations in variational inference.
method Construct a new natural gradient called the Variational Predictive Natural Gradient (VPNG).
result VPNG accounts for the relationship between model parameters and variational parameters.
Weak correlations explain linear dynamics in deep learning models.
problem Understanding the linear structure in gradient-based learning algorithms.
method Characterization of weak correlations between derivatives and parameters.
result Weak correlations are the underlying principle for linearization in deep learning models.
Algorithm improves online canonical correlation analysis.
problem Online canonical correlation analysis.
method Stochastic Scaled-Gradient Descent (SSGD) for minimizing expectation over Riemannian manifolds.
result Achieved optimal one-time-scale algorithm with explicit rate of local asymptotic convergence.
Sparse GCA finds linear relationships in multiple datasets, using gradient descent.
problem Finding linear relationships across multiple datasets with sparse loading vectors.
method Formulated as generalized eigenvalue problems, used a thresholded gradient descent algorithm.
result Proposed algorithm yields tight estimation error bounds and demonstrates effectiveness on synthetic datasets.
Neural networks can learn Boolean circuits with local correlation.
problem Learning Boolean circuits with neural networks is computationally hard.
method Observing local correlation between input patterns and target labels, focusing on tree-structured Boolean circuits.
result Local correlation determines the success or failure of optimization in learning Boolean circuits.
Randomized gradient-based ensemble improves prediction accuracy.
problem Improving prediction accuracy in machine learning.
method Randomization and gradient-based aggregation of weakly-correlated estimators.
result The method outperforms existing techniques in terms of increased accuracy.
New algorithm reduces variance in Monte Carlo simulations using deep neural networks and policy gradients.
problem Reducing variance in Monte Carlo simulations for estimating function values.
method Optimal correlation search using deep neural networks and policy gradients.
result Optimal correlation function reduces variance by approximating and calibrating policy.
We propose novel first-order stochastic approximation algorithms for canonical correlation analysis (CCA). Algorithms presented are instances of inexact matrix stochastic gradient (MSG) and inexact matrix exponentiated gradient (MEG), and achieve ε-suboptimality in the population objective in $\operatorname{poly}(\fr…
Gradient descent aligns neural feature matrices with pre-activation tangent features.
problem Understanding neural feature learning mechanisms.
method Analytical proof of alignment between weight matrices and pre-activation tangent features.
result Derivative alignment occurs almost surely in high-dimensional settings.
Study on generalization in gradient-based meta-learning, showing flatter solutions and coherence between adaptation trajectories.
problem Understanding generalization in gradient-based meta-learning.
method Analysis of objective landscapes, experimental demonstration of solution properties, and empirical evidence on coherence between adaptation trajectories.
result Meta-test solutions become flatter, lower in loss, and further away from the meta-train solution as meta-training progresses, even as generalization starts to degrade.
Gradient boosting adapted for multi-label and multi-output tasks.
problem Joint prediction of multiple classification or regression outputs.
method Gradient tree boosting with random output projections.
result Random projection improves adaptation to different output correlation patterns.
This work improves texture segmentation by automatically tuning hyperparameters for Total-Variation.
problem The challenge is to automatically select hyperparameters for Total-Variation texture segmentation.
method The approach involves extending Stein's unbiased gradient estimator to handle correlated Gaussian noise, leading to an automatic tuning method.
result The method provides an automatic way to select hyperparameters for Total-Variation texture segmentation.
New RL algorithm tackles complex discrete action spaces.
problem Challenges in applying on-policy RL in high-dimensional discrete action spaces.
method Action-value critic, correlated actions, gradient sparsification.
result Empirically outperforms related on-policy algorithms.
Multivariate boosted trees improve forecasting and control by capturing correlated predictions.
problem Capturing multivariate target cross-correlations and applying structured penalties to predictions.
method A computationally efficient algorithm for fitting multivariate boosted trees.
result Multivariate trees outperform univariate counterparts in correlated prediction scenarios.
New trees-based models handle correlated data better.
problem Standard trees-based models ignore correlation structure.
method Explicitly accounts for correlation structure in splitting criterion, stopping rules, and fitted values.
result New approach superior to standard models in simulations and real data.
Non-negative matrix factorization is a basic tool for decomposing data into the feature and weight matrices under non-negativity constraints, and in practice is often solved in the alternating minimization framework. However, it is unclear whether such algorithms can recover the ground-truth feature matrix when the wei…
GENIE balances domain-invariant feature learning and gradient alignment for improved DG performance.
problem Domain Generalization (DG) overfitting to domain-specific features
method GENIE (Generalization-ENhancing Iterative Equalizer) optimizer
result Prevents a small subset of parameters from dominating optimization, promoting domain-invariant feature learning
Gradient-based feature selection for large datasets.
problem Feature selection for large datasets with high-order correlations.
method Iterative mini-batch calculation, discrete-to-continuous relaxation.
result Efficiently finds higher-order feature correlations in both N > D and N < D regimes.
Anti-correlated noise improves machine learning model generalization.
problem Improving machine learning model generalization.
method Injecting anticorrelated noise into gradient descent steps.
result Anti-correlated noise leads to better model generalization than uncorrelated noise.
A method for accurate pricing of multidimensional derivatives under uncertain volatility.
problem High-dimensional stochastic control problem in uncertain volatility model.
method Backward actor-critic stochastic policy gradient scheme combining DP, PPO, and neural networks.
result Accurate and efficient pricing of multidimensional derivatives compared to benchmarks.
A new Adamize method improves multi-objective recommender systems.
problem Improving recommendation systems with multiple conflicting objectives.
method Developed a multi-objective model-agnostic Adamize method that corrects and stabilizes gradients.
result Significant improvements in recommendation systems, measured by hypervolume, coverage, and spacing.
GradiVeQ reduces CNN training time by 50% with 5X faster gradient aggregation.
problem Significant communication costs in gradient aggregation for distributed CNN training.
method GradiVeQ uses PCA to vector quantize gradients for direct RAR aggregation.
result GradiVeQ reduces wall-clock gradient aggregation time by more than 5X.
Gradient descent solves sparse skill estimation in crowdsourcing.
problem Crowd-sourced worker skill estimation with sparse and irregular assignments.
method Rank-one matrix completion and projected gradient descent.
result Skill estimates converge to global optima for specific sampling matrices.
Proposes integrating random effects into deep neural networks for better predictive performance.
problem Correlated data in real-life applications are not handled well by traditional deep neural networks.
method Uses mixed models with random effects to handle correlations in deep neural networks, minimizing Gaussian negative log-likelihood with SGD.
result Improves predictive performance over natural competitors in various correlation scenarios.
Paper proves minibatch SGD for GP inference converges and improves generalization.
problem Theoretical understanding and practical use of SGD for correlated samples in Gaussian process inference.
method Proves minibatch SGD converges to a critical point with rate O(1/K) for K iterations, under certain kernel conditions.
result Minibatch SGD for GP inference improves generalization and reduces computational burden.
MGDRec optimizes multiple objectives in recommender systems.
problem Optimizing for multiple, often conflicting objectives in recommender systems.
method Stochastic multi-gradient descent approach (MGDRec).
result MGDRec outperforms state-of-the-art methods in traditional objective mixtures.
Neural networks learn faster with correlated latent variables.
problem Efficiently learning from higher-order correlations in neural networks.
method Analytical derivation and simulations of two-layer neural networks.
result Correlations between latent variables speed up learning from higher-order correlations.
ESS improves MCMC efficiency for correlated & multimodal distributions.
problem Slice Sampling's sensitivity to initial length scale and difficulty with correlated distributions.
method Adaptive tuning and parallel walkers for efficient sampling.
result ESS improves efficiency by more than an order of magnitude on correlated distributions.
New learning rate approach reveals phase transitions in SGD performance.
problem Understanding feature learning dynamics in neural networks.
method Characterizing the relationship between learning rate(s) and sample complexity for gradient-based algorithms.
result Phase transition from information exponent to generative exponent regime with different learning rates.
New bounds for KANs trained with DP-SGD, addressing correlated noise.
problem Risk bounds for Kolmogorov-Arnold Networks trained by DP-SGD with correlated noise.
method Established new optimization and population risk analysis for KANs trained with DP-SGD, addressing correlated noise.
result First optimization and population risk analysis of correlated-noise mechanisms for DP training in non-convex settings, including neural networks.
Bayesian priors for neural networks are improved by incorporating weight correlations and tail behavior.
problem Improving Bayesian priors for neural networks to better reflect true beliefs and performance.
method Analyzed summary statistics of neural network weights in different architectures and incorporated these observations into new priors.
result Improved performance on image classification datasets by using new priors that account for weight correlations and tail behavior.
Early training of deep neural networks leads to small, directionally converging weights.
problem Training dynamics of deep homogeneous neural networks with small initializations.
method Gradient flow analysis and study of KKT points for neural correlation function.
result Weights converge in direction to KKT points during early training stages.
SGE-Kriging reduces high-dimensional surrogate modelling costs.
problem High-dimensional function approximation for expensive models.
method Splitting training data into slices, using sliced likelihood function, and learning hyper-parameters from sensitivity indices.
result SGE-Kriging achieves comparable accuracy to standard GE-Kriging but with lower training costs.
Gradient flow of ReLU networks converges in low-correlation high-dimensional data.
problem Convergence of shallow ReLU networks trained on weakly interacting data.
method Gradient flow analysis with Polyak-Łojasiewicz viewpoint.
result Network width of order log(n) neurons suffices for global convergence with high probability.
Proposes Hebbian-descent for neural network learning, addressing Hebbian and gradient descent issues.
problem Learning issues with correlated data and vanishing error term in gradient descent.
method Integrates Hebbian and gradient descent principles without activation function derivatives, centering neural activities.
result Biologically plausible, convergent, and effective in online learning with correlated data.
Study reveals how neural network biases align with adversarial attack frequencies.
problem Correlation between neural network biases and adversarial attacks.
method Fourier transform analysis of network implicit bias and adversarial perturbations.
result Network bias and adversarial attack frequencies are highly correlated.
SGD recovers multiple signal vectors in noisy tensor PCA.
problem Estimating multiple signal vectors from noisy tensor observations.
method Online stochastic gradient descent (SGD) in high dimensions with detailed analysis of correlations.
result Sequential elimination of correlations allows recovery of all spikes from Np−2 samples. Gradient-based explanations correlate with Android malware classifier robustness.
problem Evasion attacks on Android malware classifiers using sparse perturbations.
method Investigated gradient-based attribution methods for explaining classifier decisions and their evenness, proposing metrics to assess adversarial robustness.
result Gradient-based explanations, especially Integrated Gradients, correlate with adversarial robustness of malware classifiers.
A new method uses model gradients to improve fairness without relying on demographic data.
problem Algorithmic fairness issues due to missing demographic information and complex interactions.
method Learning a graph of gradients to identify and improve group fairness robustly to noise.
result Significantly improves fairness without sacrificing overall accuracy.
A networked learning method for correlated data outperforms federated learning in precision.
problem Estimating models from correlated data distributed across a network.
method Local linear model estimation with network regularization and information exchange.
result The weighted ensemble average estimate converges faster and more precisely than federated learning.
Study shows gradient variance increases during deep learning training, contrary to common belief.
problem Understanding and minimizing gradient variance in deep learning models.
method Gradient Clustering method using stratified sampling to minimize gradient variance.
result Gradient variance increases during training, and smaller learning rates coincide with higher variance.
Develops methods to learn correlation potentials for time-dependent Kohn-Sham systems.
problem Learning the correlation potential for time-dependent Kohn-Sham systems.
method Optimizing a least-squares objective subject to the TDKS equation using adjoints.
result Learned correlation potential models match ground truth electron densities and can have memory.
New method finds linear relationships across multiple data blocks using proximal gradient descent with ℓ1 constraint.
problem Finding leading generalized eigenvectors for multi-block CCA.
method Proximal gradient descent with ℓ1 constraint. result Rate-optimal solution under suitable assumptions.
Paper relaxes differential privacy for correlated features, improving privacy-utility trade-off.
problem Standard differential privacy ignores feature correlation, leading to suboptimal privacy-utility balance.
method Introduces CorrDP framework that accounts for feature correlation, using total variation distance for quantification.
result CorrDP algorithms outperform standard DP in synthetic and real-world datasets with insensitive features.
Proposes a constrained labeling method for weakly supervised learning.
problem Combining weak supervision signals while navigating misleading correlations.
method Randomized constrained labeling within a defined space.
result Randomized constrained labeling converges after few iterations and outperforms other methods.
A new method for traffic data imputation considering spatiotemporal correlations.
problem Traffic data imputation, especially for high-level missing scenarios.
method Spatiotemporal regularized Tucker decomposition approach.
result The proposed method outperforms existing methods on real-world traffic datasets.
Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparameterization gradients, or gradient estimates computed via the "reparameterization trick," represent a class of noisy gradients often used in Monte Carlo variational inference (MCVI). However, when these gradient estimator…