DSIVI improves variational autoencoders by optimizing a proper lower bound on ELBO.
problem Improving variational autoencoders with implicit priors.
method Introducing DSIVI, a method that optimizes a proper lower bound on ELBO for models with semi-implicit priors and posteriors.
result DSIVI improves the performance of VampPrior, a state-of-the-art prior for variational autoencoders.
New method improves BLL models for complex datasets.
problem Limited expressive capacity of Gaussian priors in BLL models.
method Combines diffusion techniques and implicit priors for variational learning.
result Enhanced predictive accuracy and uncertainty quantification.
New method uses quotient predictor space for better PAC-Bayes bounds, reducing KL divergence and improving model performance.
problem Overparameterized models with continuous symmetries can lead to biased predictions.
method Perform PAC-Bayesian analysis on quotient predictor space, constructing a canonical prior that reflects model's implicit bias.
result The new prior reduces KL divergence and improves model performance in experiments.
Develops EB for implicit likelihoods using simulators.
problem Traditional EB assumes tractable likelihoods, SBEB handles implicit likelihoods.
method Simulation-based empirical Bayes (SBEB) connects nonparametric EB to SBI, iteratively refining EB estimates.
result SBEB improves accuracy over SBI with fixed priors.
New method uses deep learning to solve linear inverse problems.
problem Solving linear inverse problems with high-dimensional signals.
method Stochastic coarse-to-fine gradient ascent procedure using implicit prior from denoising CNN.
result General algorithm for solving linear inverse problems without additional training.
Proposes deep weight prior for improving neural network performance.
problem Improving neural network performance with limited training data.
method Defines deep weight prior (DWP) as an implicit distribution and proposes variational inference methods.
result Improves performance of Bayesian neural networks with limited data and accelerates conventional CNN training.
New method tunes prior IP to data for flexible predictive distributions.
problem Challenges in approximate inference for large models with high parameter dependencies.
method Inducing-point representation of prior IP to approximate posterior process.
result Scalable method that tunes prior IP to data and provides accurate non-Gaussian predictive distributions.
Gradient descent reveals the exact implicit bias via dual optimization for linearly separable data.
problem Characterizing the implicit bias of gradient descent on linearly separable data.
method Primal-dual analysis with smoothed margin for general losses, and exponential loss with specific step sizes.
result Proves faster convergence rates for implicit bias and margin maximization.
GATSBI uses GANs for SBI, improving posterior estimation in high dimensions.
problem Statistical inference on stochastic models without likelihoods.
method Adversarial approach to variational objective, amortized inference, implicit priors.
result GATSBI returns well-calibrated posterior estimates in high dimensions.
We introduce the implicit processes (IPs), a stochastic process that places implicitly defined multivariate distributions over any finite collections of random variables. IPs are therefore highly flexible implicit priors over functions, with examples including data simulators, Bayesian neural networks and non-linear tr…
DVIP improves on IP-based methods by using IPs as priors over latent functions.
problem Limited expressiveness of IP-based models, especially in function space.
method Proposes DVIP, a multi-layer generalization of IPs, and scalable variational inference.
result DVIP outperforms previous IP-based methods and deep GPs in regression and classification tasks.
SSMs can be poisoned with clean labels, leading to generalization failure.
problem The implicit bias of SSMs can be manipulated by including special training examples with clean labels.
method Formal proof and empirical demonstration of the phenomenon.
result SSMs can fail to generalize even with clean labels, due to the inclusion of special training examples.
The variational autoencoder (VAE) is a powerful generative model that can estimate the probability of a data point by using latent variables. In the VAE, the posterior of the latent variable given the data point is regularized by the prior of the latent variable using Kullback Leibler (KL) divergence. Although the stan…
This study improves fast non-Bayesian Poisson factorization for implicit-feedback recommendation systems.
problem Improving recommendation quality and speed for implicit-feedback data.
method Regularized Poisson models, frequentist optimization, sparse solutions.
result Frequentist approach yields better top-N recommendations with shorter fitting times.
A tuning-free method recovers jointly sparse signals in MMV using implicit regularization.
problem Recovering jointly sparse signals in MMV with minimal tuning or prior knowledge.
method Reparameterizes MMV estimation matrix into decoupled factors and applies gradient descent to a least-squares objective.
result Gradient descent dynamics exhibit a momentum-like effect, converging towards an idealized row-sparse solution.
New TD method stabilizes average-reward learning.
problem Stability issues in average-reward TD learning.
method Implicit fixed point update for average-reward TD(λ). result Improved numerical stability and broader step-size range.
New sampling methods for log-concave densities using implicit integrators.
problem Sampling from log-concave densities efficiently.
method θ-method discretization of the overdamped Langevin diffusion.
result Geometric ergodicity and stability for θ≥1/2. Gradient descent recovers low-rank matrices from corrupted measurements with double over-parameterization.
problem Robust recovery of low-rank matrices from grossly corrupted measurements.
method Gradient descent with discrepant learning rates for double over-parameterized models.
result Gradient descent with discrepant learning rates provably recovers the underlying matrix without prior knowledge on rank or sparsity.
RINS-T solves time series inverse problems robustly without pretraining.
problem Recovering original signals from corrupted time series data.
method Implicit neural solvers with robust optimization techniques.
result RINS-T achieves high recovery performance without pretraining.
FTIP uses normalizing flows to improve posterior inference in function space.
problem Challenges in posterior inference with implicit-process priors.
method FTIP uses normalizing flows to define a richer variational distribution over combination weights.
result FTIP captures asymmetric and multimodal posterior structure better than Gaussian coefficient approximations.
SGD noise has no bias advantage in online learning, contrary to offline learning.
problem The role of SGD noise in online learning.
method Extensive empirical analysis of image and language data.
result Small batch sizes do not confer any implicit bias advantages in online learning.
Enhances neural networks with prior knowledge through a composite kernel.
problem Lack of effective methods to incorporate prior knowledge into neural networks.
method Integrates a composite kernel combining a neural network kernel and a GP kernel for modeling known properties.
result Demonstrates superior performance and flexibility of the Implicit Composite Kernel (ICK) on synthetic and real-world data.
AIR-Net adapts low-rank regularization dynamically for better image completion.
problem Fixed low-rank regularization limits adaptability to different images.
method AIR-Net uses adaptive and implicit regularization parameterized by a dynamic Laplacian matrix.
result AIR-Net enhances implicit regularization and outperforms fixed methods in non-uniform missing data scenarios.
Study accelerates gradient methods in machine learning, revealing risk and stability connections.
problem Understanding the statistical risk of accelerated gradient methods in machine learning.
method Continuous-time analysis of Nesterov's accelerated gradient method and Polyak's heavy ball method for least squares regression.
result Connections between early stopping, stability, and curvature of loss function are revealed.
Dropout introduces both explicit and implicit regularization effects.
problem Understanding the full impact of dropout regularization.
method Disentangled explicit and implicit regularization effects through experiments and analytic simplifications.
result Explicit and implicit regularization effects of dropout are distinct and can be characterized analytically.
GOAT improves attention mechanisms by learning better priors.
problem Standard attention mechanisms use a naive uniform prior, limiting flexibility and generalization.
method GOAT introduces a trainable, continuous prior that replaces the uniform assumption, maintaining compatibility with optimized kernels.
result GOAT avoids representational trade-offs and learns an extrapolatable prior that combines positional flexibility with length generalization.
The paper analyzes optimal implicit bias in linear regression for over-parameterized models.
problem Finding the best generalization performance in over-parameterized linear regression.
method Asymptotic analysis of generalization performance for convex functions/potentials.
result Optimal implicit bias that achieves the best generalization error under certain conditions.
A new Gaussian process regression method infers implicit manifold structure from data.
problem Scaling Gaussian process regression to high-dimensional data.
method Proposes a fully differentiable Gaussian process regression technique that infers implicit manifold structure from data.
result Improves predictive performance and calibration of standard Gaussian process regression in high-dimensional settings.
The paper provides theoretical guarantees for transformation-based models in variational inference.
problem Theoretical justification for transformation-based models in variational inference.
method Theoretical analysis of non-linear latent variable models and Gaussian process priors.
result Theoretical guarantees for implicit variational inference, achieving optimal risk bounds and approximating the true posterior.
Bayesian framework integrates prior and data knowledge for nonlinear dynamical systems.
problem Fusing diverse prior knowledge with data for accurate model learning.
method General-purpose Bayesian inference and learning framework combining explicit and implicit prior knowledge.
result Efficient parameter marginalization and closed-form densities for online and offline inference.
Our paper characterizes how ReLU affects GD's implicit bias in high-dimensional neural networks.
problem Understanding the implicit bias of gradient descent on neural networks.
method Novel primal-dual analysis tracking predictions and coefficients.
result The implicit bias approximates the minimum-ℓ2-norm solution with high probability. Open problem: Establishing bounds for Cayley-table completion to discover discrete algorithmic axioms.
problem Discovering discrete algorithmic axioms missing in deep learning.
method Cayley-table completion as a testbed for algorithmic complexity minimization.
result Formal exact recovery bounds for Cayley-table completion.
New variational approach to deep learning via gradient descent.
problem Non-robustness and poor out-of-distribution generalization in deep learning.
method Regularize variational neural networks using gradient descent's implicit bias.
result Strong in- and out-of-distribution performance achieved without additional hyperparameter tuning.
Develops implicit MAML for efficient few-shot learning.
problem Efficient few-shot learning with limited data.
method Implicit differentiation for inner loop optimization.
result Agrees with inner loop optimizer choice and handles many gradient steps.
Proposes LDIDPs for efficient sequential data generation from latent dynamical models.
problem Challenges in generating high-fidelity sequential samples from latent dynamical models.
method Utilizes implicit diffusion processes to sample from latent dynamical processes.
result Demonstrates accurate learning of dynamics and efficient generation of high-quality sequential data.
XLVINs improve data efficiency in implicit planning by leveraging latent space.
problem Improving data efficiency in implicit planning algorithms.
method XLVINs use a high-dimensional latent space to perform planning computations, breaking the algorithmic bottleneck.
result XLVINs significantly improve data efficiency across various settings compared to value iteration-based implicit planners and model-free baselines.
Generative adversarial networks (GANs) have given us a great tool to fit implicit generative models to data. Implicit distributions are ones we can sample from easily, and take derivatives of samples with respect to model parameters. These models are highly expressive and we argue they can prove just as useful for vari…
New findings suggest latent regularization is unnecessary for high-quality image generation.
problem Improving image generation quality without latent regularization.
method Investigated the effect of latent regularization on image generation using learned priors.
result In the case of a sufficiently expressive prior, latent regularization is not necessary and may harm image quality.
Kernel-guided training stabilizes GANs by controlling discrepancies.
problem Stability and interpretability issues in GANs.
method Kernel-based regularization to control discrepancies in GAN loss function.
result Theoretical guarantees on stability of the training dynamics.
Unified framework approximates gradient descent's implicit bias in high dimensions.
problem Understanding gradient descent's behavior in overparameterized settings with convex losses.
method Unified framework for convex losses, including sensitivity analysis.
result Approximation of minimum-norm interpolation in high dimensions.
Kernel-guided training stabilizes GANs by controlling discrepancies.
problem Stability and interpretability issues in GANs.
method Kernel-based regularization to control discrepancies in GAN loss function.
result Theoretical guarantees on stability of the training dynamics.
GD iterates for non-homogeneous deep nets increase margin and converge in direction.
problem Understanding implicit bias in non-homogeneous deep networks.
method Characterization of GD iterates' properties starting from small empirical risk.
result GD iterates converge in direction despite diverging norms, satisfying KKT conditions.
New methods improve integration of external LMs with AED models.
problem Improving performance of AED models by integrating external LMs.
method Comparing and proposing novel methods to estimate implicit LM from AED models.
result Proposed methods outperform previous approaches.
Mirror flow in shallow neural networks shows similar implicit bias to gradient flow, with key differences in curvature penalties.
problem Analyzing implicit bias in shallow neural networks with mirror flow.
method Characterization through variational problems and scaled potentials.
result Mirror flow with scaled potentials induces a rich class of biases not captured by RKHS norms.
Noise in SGD affects overparameterized models, favoring sparse solutions.
problem Understanding and mitigating implicit bias in SGD with parameter-dependent noise.
method Theoretical analysis of a quadratically-parameterized model with label noise and Gaussian noise.
result SGD with label noise recovers sparse ground-truth solutions, while SGD with Gaussian noise overfits dense solutions.
Bayesian deep learning uses function-space priors to improve model uncertainty and robustness.
problem Bayesian deep learning struggles with model-specific weight-space priors that are hard to interpret and specify.
method Apply a Dirichlet prior in predictive space and perform approximate function-space variational inference.
result The approach improves uncertainty quantification, scalability, and adversarial robustness in large-scale image classification.
SAM improves generalization in overparameterized models, but its behavior in tensorized models is less understood.
problem Understanding the implicit regularization of SAM in tensorized models.
method Scale-invariance analysis and gradient flow analysis to derive Norm Deviation as a measure of core norm imbalance, and propose Deviation-Aware Scaling (DAS).
result DAS achieves competitive or improved performance over SAM, while offering reduced computational overhead.
Study connects Gaussian processes and regularization for sequence-function mappings.
problem Understanding and interpreting sequence-function maps in biology.
method Relates Gaussian process priors, regularization, and gauge fixing in overparameterized weight space.
result Established the relationship between regularized regression and Gaussian processes in function space.