New variational formula for Rényi divergences improves neural network estimation in high dimensions.
problem Estimating Rényi divergences in high-dimensional systems.
method Derive and apply a variational formula for Rényi divergences over various function spaces.
result Neural network estimators of Rényi divergences are consistent under certain conditions.
This paper analyzes privacy risks in neural network pruning and proposes a defense mechanism.
problem Privacy risks in neural network pruning due to membership inference attacks.
method Investigates the impact of pruning on prediction divergence and proposes a self-attention membership inference attack.
result Proposed defense mechanism mitigates privacy risks while maintaining sparsity and accuracy.
Unified deep metric learning approach using neural networks.
problem Learning embeddings of data and extending Euclidean distances.
method Deep Bregman divergences based on neural networks.
result Superior performance on benchmark datasets compared to existing methods.
The paper presents methods to improve uncertainty calibration in Bayesian Neural Networks.
problem Uncalibrated Bayesian Neural Networks often lead to overconfidence.
method The paper uses alpha-divergences from Information Geometry for calibration.
result Calibration using alpha-divergences provides better uncertainty estimates and is more efficient.
Neural networks estimate statistical divergences with performance guarantees.
problem Estimating statistical divergences with theoretical performance guarantees.
method Parametrizing empirical variational form by a neural network and optimizing over parameter space.
result Established non-asymptotic absolute error bounds for neural estimators of four f-divergences. AlphaNet improves supernets training with alpha-divergence.
problem Improving the uncertainty distillation in weight-sharing NAS.
method Proposes alpha-divergence for better uncertainty distillation in supernets.
result Significant improvements in model performance across various FLOPs regimes.
We review recent results about the maximal values of the Kullback-Leibler information divergence from statistical models defined by neural networks, including naive Bayes models, restricted Boltzmann machines, deep belief networks, and various classes of exponential families. We illustrate approaches to compute the max…
Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights. These models are expressive and allow efficient computation of samples and derivatives, but …
New α-divergence loss function improves neural density ratio estimation.
problem Optimization challenges in existing DRE methods, especially overfitting and high sample requirements.
method Derived α-divergence loss function (α-Div) for neural density ratio estimation. result The α-divergence loss function (α-Div) offers stable and effective optimization for DRE. The empirical NTK diverges from the NTK in classification problems during overtraining.
problem The divergence of empirical NTK from NTK in classification problems during overtraining.
method Demonstrated strictly positive definiteness of NTKs for FCNs and ResNets. Proved divergence of neural network parameters during training with cross-entropy loss.
result The empirical NTK does not uniformly converge to the NTK across all times on the training samples as the network width increases.
Gradient flows of neural networks converge to optimal values or diverge, with thresholds and asymptotic behaviors.
problem Understanding the convergence and divergence of gradient flows in neural networks.
method Analysis of gradient flows on loss landscapes of neural networks using o-minimal structures.
result Gradient flows either converge to optimal values or diverge to infinity, with thresholds and asymptotic behaviors.
The paper addresses instability in KL divergence estimation using a neural network discriminator.
problem Unstable estimation of KL divergence due to discriminator complexity.
method Using a Reproducing Kernel Hilbert Space (RKHS) to control discriminator complexity.
result Theoretical bound on error probability of KL estimates based on discriminator complexity in RKHS.
Unified framework improves neural network robustness against label noise and adversarial attacks.
problem High sensitivity of neural networks to data contamination, including label noises and adversarial perturbations.
method Unified minimum-divergence estimation problem, rSDNet framework.
result Improves robustness to label corruption and adversarial attacks while maintaining competitive accuracy on clean data.
Bayesian neural networks ignore data in infinite units limit.
problem Pathological behavior of posterior in over-parameterized networks.
method Mean-field variational inference in infinite hidden units limit.
result Posterior mean converges to zero, ignoring data.
New method tightens variational representations of divergences for faster learning.
problem Improving tightness of variational representations of divergences for faster statistical estimation.
method Improved objective functionals constructed via an auxiliary optimization problem, leveraging neural network approximation.
result Tighter variational representations can result in significantly faster learning and more accurate estimation of divergences.
The paper proposes fair regression methods for continuous sensitive variables using Rényi divergence.
problem Ensuring fairness in regression models for continuous sensitive variables.
method The paper uses Hirschfeld-Gebelein-Rényi (HGR) maximal correlation coefficient and proposes two neural network approaches to minimize it.
result Empirical results show significant improvements in fairness compared to previous methods.
Wide Bayesian neural networks have a simpler weight posterior, leading to faster MCMC sampling.
problem Sampling from the posterior of wide Bayesian neural networks is challenging.
method Introducing repriorisation, a data-dependent reparameterisation that simplifies the posterior distribution.
result The repriorisation map accelerates MCMC sampling, achieving up to 50x higher effective sample size.
Estimates causal effects using neural networks for balancing covariates.
problem Estimating causal effects from observational data.
method Neural Balancing Weights (NBW) using α-divergence for density ratio estimation. result Generalized approach for balancing multidimensional data.
Study of deep linear neural networks with proportional width and depth.
problem Lack of descriptive power in Gaussian limit of deep linear neural networks.
method Proportional infinite-width infinite-depth limit for deep linear neural networks.
result Characterization of limiting distribution as a nontrivial mixture of Gaussians.
Recently, a method called the Mutual Information Neural Estimator (MINE) that uses neural networks has been proposed to estimate mutual information and more generally the Kullback-Leibler (KL) divergence between two distributions. The method uses the Donsker-Varadhan representation to arrive at the estimate of the KL d…
Fuses posterior distributions from different datasets using KL divergence.
problem Combining information from multiple datasets with uncertainty.
method Mean field assumption, KL divergence, assign-and-average approach.
result Efficient non-parametric algorithm for fused model computation.
Paper addresses variational inference issues in Bayesian neural networks.
problem Negative infinite ELBO for function-space priors in BNNs.
method Regularized KL divergence for well-defined function-space variational inference.
result Method provides competitive uncertainty estimates for BNNs.
This paper provides performance guarantees for neural estimation of statistical distances.
problem Developing performance guarantees for neural estimation of statistical distances.
method Non-asymptotic error bounds using function approximation theorems and empirical process theory.
result Established a fundamental tradeoff between approximation and estimation errors in neural estimation of statistical distances.
Paper proposes a method to stabilize estimation of KL divergence using a discriminator in RKHS.
problem High variance and instability in estimating KL divergence using neural network discriminators.
method Developed a novel construction of the discriminator in RKHS, controlled its complexity, and proved the consistency of the estimator.
result Reduced variance and stabilized training of KL divergence estimates.
A new upper bound for variational inference improves the efficiency of Bayesian deep learning.
problem Improving variational inference in Bayesian deep learning.
method Presented a new upper bound (EUBO) for evidence, derived from KL-divergence and log marginal likelihood, and used SGD for optimization.
result The new upper bound (EUBO) is tighter than previous methods and outperforms state-of-the-art results in Bayesian neural networks.
Study on critical points in random neural networks, revealing three regimes based on activation function.
problem Investigating the expected number of critical points in random neural networks.
method Deriving asymptotic formulas for critical points under infinite-width limit and suitable regularity conditions.
result Three distinct regimes of critical points behavior depending on activation function.
Deep networks can approximate high-dimensional distributions from low-dimensional ones.
problem Approximating high-dimensional distributions from low-dimensional ones.
method Proved neural networks can transform low-dimensional distributions to high-dimensional ones with arbitrary closeness measured by Wasserstein distances and maximum mean discrepancy.
result Upper bounds of the approximation error are obtained in terms of the width and depth of neural network.
New method improves deep neural network performance in regression tasks.
problem Improving generalization, robustness, and explainability of deep neural networks in regression.
method Developed a new Information Bottleneck approach using Cauchy-Schwarz divergence.
result Demonstrated superior performance on six real-world regression tasks.
Proposes NRS to find flat minima in deep neural networks.
problem Finding optimal solutions in deep neural networks with overparameterization.
method NRS leverages the concept of flat minima and uses Kullback-Leibler divergence to regularize the neighborhood region in weight space.
result NRS drives optimizers towards flat minima, improving generalization ability across various model architectures.
Variational Bayesian neural networks (BNNs) perform variational inference over weights, but it is difficult to specify meaningful priors and approximate posteriors in a high-dimensional weight space. We introduce functional variational Bayesian neural networks (fBNNs), which maximize an Evidence Lower BOund (ELBO) defi…
The paper improves risk certificate tightness for neural networks using PAC-Bayes bounds.
problem Improving the usability of risk certificates for neural networks based on PAC-Bayes bounds.
method Theoretical contributions including KL divergence bounds, efficient methodology for optimization, and methods for optimizing non-differentiable objectives.
result First non-vacuous generalization bounds on CIFAR-10 for neural networks.
Proposes a new neural head for asymmetric representation learning.
problem Asymmetric representation learning in directed relations.
method Role-aware neural convex divergence head.
result Role-aware projections improve directional accuracy over plain ICNN-Bregman heads.
New robust learning framework for regression NNs using β-divergences.
problem Outliers and data contamination in regression NNs training.
method Proposes rRNet based on β-divergence for robust learning of regression NNs.
result rRNet achieves optimal 50% asymptotic breakdown point for all β ∈ (0, 1].
New method uses neural networks to solve complex PDEs from optimal control theory.
problem Solving high-dimensional Hamilton-Jacobi-Bellman PDEs.
method Iterative diffusion optimization techniques, focusing on path measures and divergences.
result Favourable properties of log-variance divergence for Monte Carlo estimators.
New differential geometry perspective on orthogonal RNNs.
problem Mitigating exploding and vanishing gradients in RNNs.
method Using tools from differential geometry, parameterizing vector fields via directional derivatives of scalar functions.
result Our approach achieves comparable or better results on benchmark tasks.
This work explores function-space inference using KL divergence and proposes Bayesian linear regression as a benchmark.
problem Approximating the predictive posterior distribution of Bayesian models without parameter posterior approximation.
method Employing Kullback-Leibler divergence and proposing featurized Bayesian linear regression as a benchmark.
result Minimizing KL divergence leads to an ill-defined objective function, highlighting limitations of this approach.
Estimates proper calibration errors and refinement terms in probabilistic predictions.
problem Lack of a general estimator for proper calibration errors and refinement terms with known statistical properties.
method Proposes a method for consistent, asymptotically unbiased estimation of proper calibration errors and refinement terms.
result Proves the relation between refinement and f-divergences, implying information monotonicity in neural networks.
We present a method for explaining the image classification predictions of deep convolution neural networks, by highlighting the pixels in the image which influence the final class prediction. Our method requires the identification of a heuristic method to select parameters hypothesized to be most relevant in this pred…
Neural networks can model chaos efficiently by becoming geometrically chaotic.
problem Lack of theoretical understanding of how neural networks learn chaos.
method Employed a geometric perspective to show neural networks can model chaotic dynamics.
result Neural networks can reconstruct strange attractors and accurately predict local divergence rates.
A new optimisation framework for neural networks without hyperparameters.
problem Lack of explicit architectural information in optimisation frameworks.
method Extends mirror descent to account for neural architecture, transforming a Bregman divergence.
result Automatic gradient descent: a first-order optimiser without hyperparameters.
The paper shows deep neural networks have no bad local minima and no diverging paths to infinity.
problem The risk of diverging to infinity in deep neural networks.
method Mathematical analysis of regularizers and loss functions.
result For a large class of over-parameterized deep neural networks, the loss function has no bad local minima and no decreasing paths to infinity.
Variational inference with α-divergences has been widely used in modern probabilistic machine learning. Compared to Kullback-Leibler (KL) divergence, a major advantage of using α-divergences (with positive α values) is their mass-covering property. However, estimating and optimizing α-divergences require to use importa…
AES uses α-divergence to select informative points for BO, improving optimization performance.
problem Optimizing complex functions with limited evaluations.
method AES uses α-divergence to select points based on dependency with global maximum.
result AES outperforms other information-based acquisition functions in various experiments.
Optimizes deep neural network initialization variance for better performance.
problem Improving deep neural network performance through optimal initialization variance.
method Using SGD dynamics and Fokker-Planck equations, we study the relationship between initialization and expected loss function.
result An optimal condition for initialization variance that leads to lower training loss and higher test accuracy.
Automates VI divergence selection for efficient few-shot learning.
problem Efficiently selecting divergence measures for VI to improve performance.
method Meta-learning algorithm to learn optimal divergence metric and variational parameter initialization.
result Meta-learning approach outperforms standard VI methods across various tasks.
Paper introduces f-divergence variational inference for broader application.
problem Variational inference limited to specific divergences.
method Generalizes variational inference to all f-divergences using f-divergence minimization.
result Unified framework for variational inference with arbitrary f-divergences.
Introduces TDRC to balance TD's ease and soundness.
problem TD learning's instability and divergence issues.
method Gradient Temporal-Difference Learning with Regularized Corrections (TDRC).
result TDRC performs as well as TD when TD works, but is sound in divergent cases.
Physics-informed neural networks improve baryonic predictions from dark matter simulations.
problem Recreating hydrodynamic simulations from dark matter requires expensive and time-consuming computations.
method Combining neural network architectures with physical constraints and using Kullback-Leibler divergence for prediction comparison.
result Improved accuracy of baryonic predictions based on dark matter halo properties, successful recovery of the metallicity relation, and preserved scatter.