Paper proves LCVB method's consistency in Bayesian posteriors and decision rules.
problem Approximating Bayesian posteriors and decision rules.
method Loss-calibrated variational Bayes (LCVB) method.
result LCVB method's consistency in both approximate posterior and decision rules.
This tutorial derives the VAE loss function under Gaussian assumptions.
problem Computational intractability of posterior distributions in Bayesian machine learning.
method Derives the variational lower bound loss function of a standard VAE.
result The Kullback-Leibler divergence has a closed form solution under Gaussian assumptions.
VarGrad reduces variance in ELBO gradient estimation for variational inference.
problem Improving the variance of gradient estimators in variational inference.
method VarGrad uses a new log-variance loss to estimate the ELBO gradient, achieving lower variance than the score function method.
result VarGrad offers a lower variance gradient estimator compared to other methods.
This work interprets SFA through variational inference, relaxing linearity constraints.
problem Recover non-linear SFA from variational inference.
method Probabilistic interpretation of SFA through variational inference, relaxing linearity constraints.
result Reinterprets SFA as a variational framework, allowing slowness as a regularizer to reconstruction loss.
Proposes variational Gaussian approximations for solving the Kushner equation.
problem Solving the Kushner equation for state estimation with observations.
method Tractable variational Gaussian approximations of proximal losses based on Wasserstein and Fisher metrics.
result The proposed method leads to a Gaussian flow consistent with Kalman-Bucy and Riccati flows.
New method prevents neural network breakdown by combining trimmed loss and variation regularization.
problem Outlier contamination in neural network training.
method Integrates transformed trimmed loss and higher-order variation regularization.
result Ensures robustness to outlier contamination with a high functional breakdown point.
New reweighted losses improve diffusion model training and image quality.
problem Training and improving diffusion models for image generation.
method Constructing a cascade of time-dependent variational lower bounds.
result Significant improvements in pixel-space image modeling quality.
We analyze bias-variance of margin losses.
problem Understanding model overfitting/underfitting.
method Bias-variance decomposition for strictly convex margin losses.
result Expected risk decomposes into central model risk and data variation.
The paper bounds information losses in neural classifiers from sampling.
problem Information losses in neural classifiers from finite datasets.
method Proves a relationship between information losses and expected total variation of the estimated neural model, bounds this expected total variation as a function of dataset size.
result Obtains bounds on information losses that are less sensitive to input compression and much smaller than existing bounds.
Stable GFlowNets prevent loss spikes and mode collapse in training.
problem Unstable training of GFlowNets leading to loss spikes and mode collapse.
method Assessed sensitivity of GFlowNet objectives, derived loss-to-TV bounds, and proposed Stable GFlowNets.
result Stable GFlowNets improve training behavior and distributional fidelity.
As deep Variational Auto-Encoder (VAE) frameworks become more widely used for modeling biomolecular simulation data, we emphasize the capability of the VAE architecture to concurrently maximize the timescale of the latent space while inferring a reduced coordinate, which assists in finding slow processes as according t…
New method for better initializations in variational Bayes for deep models.
problem Effective initializations for stochastic variational inference in deep models.
method Layer-wise initialization strategy based on Bayesian linear models.
result Faster and better convergence compared to alternatives.
Prb-GAN uses dropout and variational inference to improve GAN performance.
problem GANs struggle with mode loss and training instability.
method Introduces Prb-GANs with dropout and variational inference for parameter distribution.
result Improves GAN performance through dropout and variational inference.
Paper introduces a variational approach for PU learning with improved performance and stability.
problem Learning binary classifiers from only positive and unlabeled data.
method Variational principle for PU learning, quantitatively evaluating modeling error, efficient loss function, margin maximizing loss function.
result Improved discriminative performance and numerical stability of the variational PU learning method.
Study optimal consumption for loss-averse agents considering past spending peaks.
problem Optimal consumption for loss-averse agents with reference to past spending maximum.
method Adopted S-shaped utility, concave envelope, HJB variational inequality, dual transform, and smooth-fit conditions.
result Obtained piecewise closed-form solutions for optimal consumption and investment control.
Geometric Mean Market Makers super-hedge impermanent loss without models.
problem Super-hedging impermanent loss in Geometric Mean Market Makers.
method Model-free rebalancing strategy.
result Loss-versus-rebalancing vanishes due to finite variation exchange rate.
Variational neural networks optimize activation functions using gradient descent.
problem Lack of guiding principles for choosing activation functions in neural networks.
method Variational neural networks use a linear combination of candidate functions, optimizing via gradient descent.
result Optimal activation functions can be found using gradient descent.
AutoBayes simplifies variational inference by composing models and optimizing them.
problem Generalized variational inference complexities and optimization challenges.
method Compositional framework exploiting chain rules for automatic differentiation.
result Optimized models and parameterized statistical games can be locally optimized.
This paper analyzes output activation functions for adversarial losses.
problem Understanding which output activation functions form a well-behaved adversarial loss.
method Variational divergence minimization and a comparative framework for adversarial losses.
result There is no single winning combination of output activation functions and regularization approaches across all settings.
Improved sampling via learned diffusions using variational losses.
problem Sampling from target distributions without direct access to samples.
method Generalized Schrödinger bridge problem, variational formulation, gradient-based optimization.
result Proposed log-variance loss leads to improved performance.
In this paper, we introduce a new form of amortized variational inference by using the forward KL divergence in a joint-contrastive variational loss. The resulting forward amortized variational inference is a likelihood-free method as its gradient can be sampled without bias and without requiring any evaluation of eith…
The paper introduces variational characterizations for local entropy and heat regularization in deep learning.
problem Understanding and optimizing loss regularizations in deep learning.
method Introducing variational characterizations and a two-step optimization scheme based on iterative shift and best Gaussian approximation in Kullback-Leibler divergence.
result The optimization schemes for local entropy and heat regularized loss differ only over the argument of the Kullback-Leibler divergence used for best Gaussian approximation.
DAEs can generate images without additional loss terms, inheriting VAE properties.
problem Difficulty in using VAEs for practical generative modelling.
method Empirical exploration of DAEs for image generation without novel methods.
result DAEs can generate images successfully without additional loss terms.
Neural networks solve variational inequalities for optimal stopping problems.
problem Solving variational inequalities for optimal stopping problems in finance.
method Proposed neural network approach using loss functions directly incorporating variational inequality on whole domain.
result Existence and convergence of neural networks whose losses converge to zero.
New bound shows variational algorithms may struggle with barren plateaus.
problem Barren plateaus in quantum loss landscapes.
method General bound on loss variance and gradient decay.
result Exponential decay of gradients in subregions of barren plateaus.
Paper provides finite-sample guarantees for Wasserstein DRO without dimensionality curse.
problem Tackles empirical success of Wasserstein DRO in operations and ML with performance guarantees.
method Develops non-asymptotic framework for analyzing out-of-sample performance and generalization bound.
result First finite-sample guarantee for generic Wasserstein DRO problems without curse of dimensionality.
VarNet solves PDEs with deep neural networks using variational loss.
problem Solving partial differential equations (PDEs) efficiently and accurately.
method VarNet uses a novel variational loss function and optimizes space-time samples for training deep neural networks.
result VarNet models are smooth, differentiable, and directly usable for PDE control and optimization.
In this paper, we provide an information-theoretic interpretation of the Vector Quantized-Variational Autoencoder (VQ-VAE). We show that the loss function of the original VQ-VAE can be derived from the variational deterministic information bottleneck (VDIB) principle. On the other hand, the VQ-VAE trained by the Expect…
Score matching fails to train VAEs robustly, revealing autoencoding loss insights.
problem Catastrophic failure of variational score matching on VAE models.
method Analysis of existing variational score matching objectives and their equivalence to autoencoding losses.
result Score matching methods fail to produce robust VAE models, predicting poor performance.
Proposes an amortized variational framework for Deep Q Networks.
problem Efficient exploration in deep reinforcement learning.
method Amortized variational inference for action value function approximation.
result Significantly less learning parameters and better performance.
Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates. In the discrete case, one can perform reparametrization using the Gumbel-Max trick, but the resulting objective relies on an argmax operation and is non-dif…
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. 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.
Wasserstein distributionally robust optimization (DRO) has recently achieved empirical success for various applications in operations research and machine learning, owing partly to its regularization effect. Although connection between Wasserstein DRO and regularization has been established in several settings, existin…
We propose a framework that directly tackles the probability distribution of the value function parameters in Deep Q Network (DQN), with powerful variational inference subroutines to approximate the posterior of the parameters. We will establish the equivalence between our proposed surrogate objective and variational i…
We unify f-divergences, Bregman divergences, surrogate loss bounds (regret bounds), proper scoring rules, matching losses, cost curves, ROC-curves and information. We do this by systematically studying integral and variational representations of these objects and in so doing identify their primitives which all are rela…
This paper introduces Wasserstein variational inference, a new form of approximate Bayesian inference based on optimal transport theory. Wasserstein variational inference uses a new family of divergences that includes both f-divergences and the Wasserstein distance as special cases. The gradients of the Wasserstein var…
We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called "adversarial losses", which, besides classical Lp losses, includes maximum mean discrepancy (MMD), Wasserstein distance, and total variation distance. These losses are closely related to the …
In recent years Variation Autoencoders have become one of the most popular unsupervised learning of complicated distributions.Variational Autoencoder (VAE) provides more efficient reconstructive performance over a traditional autoencoder. Variational auto enocders make better approximaiton than MCMC. The VAE defines a …
A new method improves molecule generation accuracy and efficiency.
problem Posterior collapse in VAEs for molecule sequence generation.
method Re-balancing reconstruction loss to avoid posterior collapse.
result Our method achieves state-of-the-art reconstruction accuracy and competitive validity.
CosmoVAE uses deep learning to fill in missing parts of the cosmic microwave background map.
problem Missing observations in the CMB map due to thermal dust noise.
method Variational autoencoder (VAE) trained with a new loss function.
result CosmoVAE achieves state-of-the-art performance in CMB map inpainting.
New algorithms minimize dynamic regret for strongly convex losses.
problem Minimizing dynamic regret for strongly convex losses.
method Developed Strongly Adaptive algorithms exploiting KKT conditions.
result Achieved near optimal dynamic regret of O(d1/3n1/3extTV[u1:n]2/3∨d). GCVAE improves disentanglement in VAEs while balancing reconstruction error.
problem Improving disentanglement in VAEs while maintaining low reconstruction error.
method Introduces three controllable Lagrangian hyperparameters to optimize reconstruction and KL divergence loss.
result GCVAE outperforms state-of-the-art models in disentanglement while balancing reconstruction.
A new loss function ED simplifies training energy-based models without scores.
problem Training energy-based models is computationally expensive.
method Energy Discrepancy (ED) loss function that does not rely on scores or MCMC.
result ED effectively interpolates between score matching and negative log-likelihood.
TA-VAAL improves active learning by better utilizing task structures and overall data distribution.
problem High labeling cost limits deep learning applications; active learning selects informative samples.
method Task-aware variational adversarial active learning (TA-VAAL) modifies VAAL by relaxing task loss prediction and using ranking loss information.
result TA-VAAL outperforms state-of-the-arts on various datasets, including balanced and imbalanced labels.
Recurrent neural networks show state-of-the-art results in many text analysis tasks but often require a lot of memory to store their weights. Recently proposed Sparse Variational Dropout eliminates the majority of the weights in a feed-forward neural network without significant loss of quality. We apply this technique …
This work provides statistical guarantees for VAEs using PAC-Bayesian theory.
problem Theoretical properties of VAEs remain open questions.
method PAC-Bayesian theory to derive statistical guarantees.
result Upper bounds on Wasserstein distance between input and generative model.
This work focuses on dynamic regret of online convex optimization that compares the performance of online learning to a clairvoyant who knows the sequence of loss functions in advance and hence selects the minimizer of the loss function at each step. By assuming that the clairvoyant moves slowly (i.e., the minimizers c…