Paper presents a rank-1 approximation method for natural policy gradients in deep RL.
problem Computing natural gradients requires inverting the Fisher Information Matrix, which is computationally expensive.
method Develops a rank-1 approximation to the inverse Fisher Information Matrix for efficient natural policy optimization.
result The rank-1 approximation converges faster and has similar sample complexity to stochastic policy gradient methods.
PAMA learns covariate importance for better matching in observational studies.
problem Poor performance of conventional matching methods when covariates differ in relevance.
method PAMA is a semi-supervised framework that learns covariate importance from paired data and optimizes a weighted quadratic score.
result PAMA outperforms standard methods, particularly in high-dimensional settings and under model misspecification.
In the analysis of machine learning models, it is often convenient to assume that the parameters are IID. This assumption is not satisfied when the parameters are updated through training processes such as SGD. A relaxation of the IID condition is a probabilistic symmetry known as exchangeability. We show the sense in …
Paper proposes efficient weight updates for edge nodes with minimal communication.
problem Inefficient and resource-intensive full weight updates for edge nodes.
method Deep partial updating, selecting a subset of weights to update.
result Achieves similar performance with fewer weight updates.
Paper analyzes ensemble Kalman updates for effective dimension and localization.
problem Why small ensemble sizes work well in inverse problems and data assimilation.
method Non-asymptotic analysis of ensemble Kalman updates, focusing on effective dimension and localization.
result Rigorously explains why a small ensemble size is sufficient when prior covariance has moderate effective dimension.
A new method estimates parameters in heavy-tailed corrupted regression with unknown covariance and heterogeneous noise.
problem Estimating parameters in regression with heavy-tailed errors and unknown covariance.
method Near-optimal computationally tractable estimator based on power method and Multiplicative Weight Update algorithm.
result The estimator achieves the optimal statistical rate and breakdown-point under near-optimal sample size.
Proposes a method to improve learning when training data is not representative.
problem Improving supervised learning when training data is not representative (covariate shift).
method Conditioning on propensity scores to balance covariates within strata.
result Significantly improved target prediction and AUC (0.958) on supernovae classification challenge.
Long Short-Term Memory networks trained with gradient descent and back-propagation have received great success in various applications. However, point estimation of the weights of the networks is prone to over-fitting problems and lacks important uncertainty information associated with the estimation. However, exact Ba…
Framework explains how dual deep networks learn features from unlabeled data.
problem Understanding self-supervised learning with dual deep networks.
method Theoretical framework and hierarchical latent tree model.
result Deep ReLU networks learn latent variables through contrastive SSL.
Proofs high-dimensional spectrum convergence of weighted sample covariance.
problem High-dimensional spectrum convergence of weighted sample covariance.
method Proposes a new, concise proof with stronger assumptions.
result Spectrum convergence proven for different weight distributions.
This paper improves Gaussian process predictions by integrating prior knowledge.
problem Gaussian processes lack predictive power when prior information is ignored.
method Derive mean and covariance functions from previous data using weighted sums of basis functions.
result Integrating prior knowledge significantly increases look-ahead time and accuracy.
We show that deep networks can be trained using Hebbian updates yielding similar performance to ordinary back-propagation on challenging image datasets. To overcome the unrealistic symmetry in connections between layers, implicit in back-propagation, the feedback weights are separate from the feedforward weights. The f…
In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible. At encoder side, we fine-tune a pre-trained artifact removal network on target data by using a compression objective applied on the weight-u…
New method improves covariance estimation for weighted samples.
problem Improving covariance estimation for weighted sample data.
method Asymptotic non-linear shrinkage formulas for covariance and precision matrix estimators of weighted sample covariances.
result Asymptotic non-linear shrinkage formulas for covariance and precision matrix estimators of weighted sample covariances.
RSO uses random weight perturbations to train deep networks without gradients.
problem Training deep neural networks efficiently and without gradient information.
method RSO is a gradient-free Markov Chain Monte Carlo approach that updates weights based on mini-batch loss reduction.
result RSO achieves high accuracy (99.1% on MNIST) with significantly fewer updates than traditional methods.
Paper proves multiplicative weight updates can train neural networks without learning rate tuning.
problem Vanishing and exploding gradients in gradient descent for compositional functions.
method Proves descent lemma for compositional functions using multiplicative weight updates and derives Madam optimizer.
result Madam optimizer trains state-of-the-art neural networks without learning rate tuning.
We describe k-MLE, a fast and efficient local search algorithm for learning finite statistical mixtures of exponential families such as Gaussian mixture models. Mixture models are traditionally learned using the expectation-maximization (EM) soft clustering technique that monotonically increases the incomplete (expec…
Sparse Inverse Covariance Estimation (SICE) is useful in many practical data analyses. Recovering the connectivity, non-connectivity graph of covariates is classified amongst the most important data mining and learning problems. In this paper, we introduce a novel SICE approach using adaptive thresholding. Our method i…
Study nonparametric contextual bandits with batched updates, achieving optimal regret.
problem Optimal regret in nonparametric contextual bandits with batch constraints.
method Dynamic binning of covariate space, optimal regret achieved.
result Achieves optimal regret (up to logarithmic factors) for nonparametric contextual bandits.
Model analyzes cooccurrence data for recommender systems and item relevance.
problem High-dimensional cooccurrence data from online platforms.
method Shared parameter Alternating Tweedie (SA-Tweedie) model with Fisher scoring and learning rate adjustment.
result SA-Tweedie model outperforms other methods in optimizing parameters.
Online learning makes sequence of decisions with partial data arrival where next movement of data is unknown. In this paper, we have presented a new technique as multiple times weight updating that update the weight iteratively forsame instance. The proposed technique analyzed with popular state-of-art algorithms from …
Fast covariance calculation is required both for SLAM (e.g.~in order to solve data association) and for evaluating the information-theoretic term for different candidate actions in belief space planning (BSP). In this paper we make two primary contributions. First, we develop a novel general-purpose incremental covaria…
New method for inference on covariates in NMF with random effects.
problem Formal inference for covariate effects in NMF with non-negativity constraints.
method NMF-RE model with random effects, ridge updates, df-based cap, asymptotic linearization, wild bootstrap.
result Valid inference on covariates with non-negativity constraint, avoiding degeneracy.
CDST improves ensemble prediction by adjusting model weights based on covariates.
problem Improving ensemble prediction accuracy in complex scenarios.
method Covariate-dependent stacking (CDST) with flexible model weights estimated via cross-validation.
result CDST consistently outperforms conventional model averaging methods in complex datasets.
The paper analyzes how re-weighting helps in reducing variance in high-dimensional kernel methods under covariate shifts.
problem The challenge of high-dimensional kernel methods under covariate shifts and the role of re-weighting.
method Derives asymptotic expansion of high-dimensional kernels under covariate shifts, analyzes bias-variance decomposition, and characterizes the regularized kernel.
result Re-weighting helps in decreasing variance and can be seen as a data-dependent regularization.
Bio-inspired neural networks use predictive coding for efficient weight updates.
problem Training artificial neural networks efficiently and biologically plausibly.
method Predictive Coding (PC) updates weights locally using only local information.
result PC provides theoretical advantages like automatic gradient scaling.
New criterion improves predictive evaluation in weighted inference scenarios.
problem Improving predictive evaluation in scenarios with different likelihoods for estimation and evaluation.
method Developed the posterior covariance information criterion (PCIC) to handle weighted likelihood inference.
result PCIC is asymptotically unbiased for quasi-Bayesian generalization error in weighted inference.
WeSpeR speeds up non-linear shrinkage for high-dimensional weighted covariance.
problem Computing non-linear shrinkage formulas for high-dimensional weighted sample covariance.
method Derive extit{WeSpeR} algorithm using asymptotic sample spectrum properties.
result Significantly speeds up non-linear shrinkage in dimensions higher than 1000.
Improves BBVI for high-dimensional Gaussian approximations by using low-rank approximations.
problem Scalability issues with BBVI for high-dimensional multivariate Gaussian approximations.
method Extends BaM framework to handle full covariance matrices by integrating patch step for low-rank parameterization.
result Shows improved efficiency and scalability on synthetic and real-world high-dimensional inference problems.
Recently, a lot of effort has been paid to the efficient computation of Kriging predictors when observations are assimilated sequentially. In particular, Kriging update formulae enabling significant computational savings were derived in Barnes and Watson (1992), Gao et al. (1996), and Emery (2009). Taking advantage of …
Proposes a new method to adapt to covariate shifts in supervised learning.
problem Covariate shift in training and testing samples with different marginal distributions.
method Minimax risk classification (MRC) approach that weights both training and testing samples.
result Significantly enhanced classification performance in synthetic and empirical experiments.
Paper proposes a new activation function to reduce overfitting and large weight update issues.
problem Overfitting and large weight update problems in neural networks.
method Introduces a new activation function called Thresholded Exponential Rectified Linear Units (TERELU).
result TERELU shows better performance in reducing overfitting and large weight update issues compared to other activation functions.
The paper proposes a new method for covariate balancing using IPM to improve causal inference.
problem Covariate imbalance in causal inference weighting methods, especially when models are not correctly specified.
method The integral probability metric (IPM) is used to determine optimal weights for treated and control groups.
result The proposed method can be consistent without specifying either the propensity score or outcome regression model.
This paper optimizes deep learning training by efficiently sharding weight updates across replicas.
problem Redundant weight update computation on all replicas in data-parallel training.
method Automatic sharding of weight updates using static analysis and transformations on the training graph.
result Substantial speedups achieved on large-scale models using Cloud TPUs.
ITSPACE improves covariance alignment faster than other methods.
problem Optimizing covariance matrices for machine learning tasks.
method Proximal majorization-minimization method that directly optimizes the Bures-Wasserstein objective.
result ITSPACE achieves lower BW gap solutions faster than other methods.
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…
The paper calculates sensitivities for financial derivatives using path weighting methods.
problem Computing sensitivities for path-dependent financial derivatives with high variance and degeneracy issues.
method Proposes explicit path weighting formula, variance reduction adjustment, and covariance inflation technique.
result Effective methods to address high variance and degeneracy in sensitivities computation.
The paper proves a new method to improve generalization in covariate-shift scenarios.
problem Improving performance on test distributions that differ from training distributions.
method Independence-driven importance weighting algorithms for feature selection.
result Theoretical proof that these algorithms can identify optimal variables for covariate-shift generalization.
DACE estimates covariance from compressed data, improving accuracy.
problem Estimating covariance from large, distributed data.
method Data-aware weighted sampling for unbiased estimation.
result DACE provides more accurate covariance estimation under compression.
Regularized EM algorithm improves GMM clustering in low sample settings.
problem Numerical instability and convergence issues in EM-GMM for low sample support.
method Regularized EM algorithm that maximizes penalized GMM likelihood, ensuring positive definiteness and structured covariance matrices.
result The regularized EM algorithm leads to better performing EM for structured covariance matrix models or low sample settings.
Fewer data weight updates lead to faster convergence in machine learning models.
problem Improving robustness of machine learning models through data mixing.
method Analyzing convergence behavior of data mixing with a finite number of inner steps.
result The optimal number of inner steps scales with the budget and type of gradients used.
A new method uses nearest neighbors for importance weighting.
problem Data covariate shift problems in machine learning.
method Nearest neighbor classification scheme for determining importance weights.
result Demonstrated effectiveness through comparative experiments on various classification tasks.
Unified approach to linear regression using covariance fitting for optimal weights.
problem Finding optimal weights for linear regression models when weights are unknown.
method Covariance fitting SPICE-methodology to obtain data-adaptive weights.
result Tuned versions of known regularized estimators are unified under a common approach.
MELO predicts electricity loads by adapting to shifts without external indicators.
problem Adapting to non-stationary prediction challenges in online settings.
method MELO combines multiple forgetting factors and aggregation rules to adaptively predict.
result MELO reduces RMSE by 34.7% compared to base predictors and external covariates.
Bayesian optimization (BO) is a widely-used method for optimizing expensive (to evaluate) problems. At the core of most BO methods is the modeling of the objective function using a Gaussian Process (GP) whose covariance is selected from a set of standard covariance functions. From a weight-space view, this models the o…
SpecGD mitigates misalignment in phase retrieval models with anisotropic inputs.
problem Misalignment during gradient descent in phase retrieval models with anisotropic inputs.
method Spectral gradient descent modifies gradient updates to preserve directional information and remove spike amplification.
result SpecGD removes spike amplification, leading to stable alignment and accelerated noise contraction.
This short note reviews so-called Natural Gradient Descent (NGD) for multivariate Gaussians. The Fisher Information Matrix (FIM) is derived for several different parameterizations of Gaussians. Careful attention is paid to the symmetric nature of the covariance matrix when calculating derivatives. We show that there ar…
We review recent probabilistic results on covariant Schrödinger operators on vector bundles over (possibly locally infinite) weighted graphs, and explain applications like semiclassical limits. We also clarify the relationship between these results and their formal analogues on smooth (possibly noncompact) Riemannian m…