Bayesian deep learning faces posterior collapse due to likelihood vs. prior competition.
problem Posterior collapse in Bayesian deep learning models.
method Identified competition between likelihood and prior regularization in a linear latent variable model.
result Posterior collapse is related to neural and dimensional collapse, suggesting a broader learning issue.
The study characterizes and rules out collapsing in convex ancient mean curvature flow.
problem Characterizing and ruling out collapsing in convex ancient mean curvature flow.
method Characterization and counterexamples.
result Collapsing occurs if and only if the flow is asymptotic to at least one Grim hyperplane.
This paper examines how skip connections prevent rank collapse in sequence models.
problem Rank collapse in sequence models, leading to reduced expressivity and training instabilities.
method Analytical and ablation studies of lambda-skip connections in SSMs.
result A sufficient condition to prevent rank collapse across various architectures.
New study shows MLE can avoid model collapse with gradual synthetic data addition.
problem Model collapse in generative models trained on synthetic data.
method Theoretical study of maximum likelihood estimation (MLE) under iterative training with accumulating synthetic data.
result Non-asymptotic bounds show MLE can avoid model collapse even as real data fraction vanishes.
Model collapse occurs even with minimal synthetic data, and larger models can exacerbate it.
problem Model collapse in large neural networks due to synthetic data.
method Theoretical and empirical investigation of model collapse in various neural network architectures.
result Model collapse is exacerbated by larger models, but not entirely prevented.
Study on model collapse in regression models, proposing a mitigation strategy.
problem Model collapse in recursive training of regression models.
method Analytic formulae and adaptive regularization strategy.
result Modified scaling laws and mitigation strategy for model collapse.
Large models collapse epistemic uncertainty, challenging traditional wisdom.
problem Epistemic uncertainty collapse in large models.
method Implicit ensembling and decomposition techniques.
result Larger models can collapse epistemic uncertainty, contrary to expectations.
Stochastic variational inference for collapsed models has recently been successfully applied to large scale topic modelling. In this paper, we propose a stochastic collapsed variational inference algorithm for hidden Markov models, in a sequential data setting. Given a collapsed hidden Markov Model, we break its long M…
New findings show DNC is not optimal for deep models, revealing a low-rank bias.
problem Theoretical limitations of DNC in non-linear models and multi-class classification.
method Analysis of non-linear models of arbitrary depth in multi-class classification.
result DNC stops being optimal for DUFM when going beyond two layers or two classes, due to a low-rank bias.
Mathematical analysis shows annealing prevents mode collapse in Gaussian mixtures.
problem Mode collapse in variational inference for multimodal distributions.
method Analyzed annealing strategies for Gaussian mixtures, derived formulas, and tested on neural networks.
result Appropriately chosen annealing schemes can robustly prevent mode collapse.
Paper tackles model collapse in synthetic data retraining.
problem Iterative retraining of generative models on synthetic data can lead to performance deterioration.
method Integrates an external synthetic data verifier to prevent model collapse.
result Synthetic retraining with a verifier can improve model performance initially but may lead to convergence to the verifier's knowledge center.
Verification helps prevent model collapse when training on synthesized data.
problem Model collapse when training on generated data.
method Theoretical characterization using Gaussian mixtures, linear classifiers, and linear verifiers to assess synthesized data quality.
result Verifiers can prevent model collapse and correlate with performance.
Variational autoencoders often collapse, showing latent variables are non-identifiable.
problem Posterior collapse in variational autoencoders due to non-identifiable latent variables.
method Proves latent variable non-identifiability causes posterior collapse. Proposes latent-identifiable models using Brenier maps and input convex neural networks.
result Latent-identifiable models resolve posterior collapse and provide meaningful representations.
New method controls posterior collapse in VAEs without network architecture constraints.
problem Posterior collapse in VAEs reduces diversity of generated samples.
method Introduces Latent Reconstruction (LR) loss to control posterior collapse.
result Controls posterior collapse on various datasets without architectural constraints.
Topic models, and more specifically the class of Latent Dirichlet Allocation (LDA), are widely used for probabilistic modeling of text. MCMC sampling from the posterior distribution is typically performed using a collapsed Gibbs sampler. We propose a parallel sparse partially collapsed Gibbs sampler and compare its spe…
New data accumulation prevents model collapse in generative models.
problem Model collapse in generative models trained on their own outputs.
method Empirical study of language models, diffusion models, and variational autoencoders; analytically tractable framework for linear models.
result Accumulating synthetic data alongside real data avoids model collapse, preventing performance degradation.
New method controls posterior collapse in VAEs with theoretical guarantees.
problem Posterior collapse in VAEs where encoder ignores latent structure.
method Inverse Lipschitz constraint on decoder network.
result Controls degree of posterior collapse for various VAE models.
Generative Adversarial Networks are known for their high quality outputs and versatility. However, they also suffer the mode collapse in their output data distribution. There have been many efforts to revamp GANs model and reduce mode collapse. This paper focuses on two of these models, PacGAN and VEEGAN. This paper ex…
This paper extends neural collapse to regression problems, revealing key features and structures.
problem Understanding the structure learned by deep neural networks in regression tasks.
method Established Neural Regression Collapse (NRC) across different models, analyzing feature and weight alignments.
result Deep neural regression models exhibit a collapsed feature space, aligning with target dimensions and covariances.
New analysis shows how attention masks and LayerNorm prevent rank collapse in transformers.
problem Rank collapse in transformer models with increasing depth.
method General analysis of rank collapse under self-attention, considering attention masks and LayerNorm.
result Self-attention with LayerNorm can prevent rank collapse and maintain a rich set of equilibria.
This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabilities. To infer the parameters of DirVAE, we utilize the stochastic gradient method by approximating the Gamma distribution, which is a comp…
We develop a framework for approximating collapsed Gibbs sampling in generative latent variable cluster models. Collapsed Gibbs is a popular MCMC method, which integrates out variables in the posterior to improve mixing. Unfortunately for many complex models, integrating out these variables is either analytically or co…
Model collapse occurs quickly for synthetic data generated by previous models.
problem Model quality degrades over recursive training on synthetic data.
method Theoretical and experimental evaluations of discrete and Gaussian distributions under near ML estimation.
result Model collapse for discrete distributions is approximately linearly dependent on the number of times a word occurs in the original corpus, and for Gaussian models, the standard deviation reduces to zero roughly at n iterations.
New model explains neural collapse and limits on minority classes in imbalanced datasets.
problem Understanding and predicting performance limits of deep learning models on imbalanced datasets.
method Layer-Peeled Model, a nonconvex optimization program isolating top layers and applying constraints.
result Reveals a new phenomenon called Minority Collapse that limits deep learning models on minority classes.
New critics improve VAEs by preventing latent collapse.
problem Posterior collapse in VAEs where latent variables are ignored.
method Inference critics that detect and incentivize meaningful latent representations.
result Optimizing inference critics increases mutual information between latent and observations.
Study collapsing geometry of hyperkähler 4-manifolds and prove conjectures.
problem Understanding collapsing geometry of hyperkähler 4-manifolds.
method Investigation of collapsing geometry and proving conjectures.
result Proved two conjectures about collapsed limits and asymptotic behavior of hyperkähler 4-manifolds.
The paper tackles model collapse in GPLVMs by improving kernel flexibility and projection variance.
problem Model collapse in GPLVMs leading to vague latent representations.
method Theoretical analysis of projection variance, integration of SM and RFF kernels, and variational inference.
result The advisedRFLVM outperforms competing models in informative latent representations and missing data imputation.
Theoretical work on mode collapse in variational inference models.
problem Mode collapse in variational inference models, where models focus on a few modes instead of all possible ones.
method Theoretical investigation of mode collapse in Gaussian mixture models, identifying key low-dimensional statistics and equations governing their evolution.
result Mode collapse is present even in favorable scenarios, driven by mean alignment and vanishing weight mechanisms.
Variational autoencoders learn distributions of high-dimensional data. They model data with a deep latent-variable model and then fit the model by maximizing a lower bound of the log marginal likelihood. VAEs can capture complex distributions, but they can also suffer from an issue known as "latent variable collapse," …
New metrics prevent event collapse in contrast maximization frameworks.
problem Event collapse in contrast maximization frameworks.
method First principles of space-time deformation based on differential geometry and physics.
result Proposed metrics mitigate event collapse and do not harm well-posed warps.
Paper explains neural collapse in neural networks using a new model.
problem Understanding neural collapse in neural networks during training.
method Introducing the unconstrained layer-peeled model (ULPM) to prove gradient flow convergence to critical points of a minimum-norm separation problem.
result Proves that all critical points are strict saddle points except the global minimizers exhibiting neural collapse.
Levenshtein VAE prevents posterior collapse in text generation models.
problem Posterior collapse in VAEs where generators ignore latent variables.
method Replaces ELBO with a Levenshtein distance-based objective to prevent collapse.
result Levenshtein VAE produces more informative latent representations.
Proves weakly non-collapsed RCD spaces are strongly non-collapsed.
problem Proving the equivalence of weakly non-collapsed and strongly non-collapsed RCD spaces.
method Analyzes properties of RCD spaces and uses auxiliary results.
result Confirms conjecture about RCD spaces being strongly non-collapsed.
Reward collapse occurs when ranking-based reward models yield uniform rewards for different prompts.
problem Reward collapse in aligning large language models with human preferences.
method Introduced a prompt-aware optimization scheme to derive closed-form expressions for reward distributions.
result Our prompt-aware utility functions significantly alleviate reward collapse during training.
Study on Neural Collapse limits in deep learning.
problem Understanding the limits of Neural Collapse in deep learning.
method Investigated Neural Collapse in the context of generalization and feature learning, refining conjectures and conducting experiments.
result Neural Collapse primarily occurs on the train set and not on the test set, suggesting it is an optimization phenomenon with unclear connections to generalization.
The paper investigates model collapse in language models from a probabilistic perspective.
problem Understanding and preventing model collapse in language model training.
method Investigates recursive parametric model training from a probabilistic standpoint, characterizing conditions for model collapse and proposing mitigation strategies.
result Progressively increasing sample size is necessary to prevent model collapse, with a superlinear growth rate required in the asymptotic regime.
A new method improves Bayesian deep learning by balancing scalability and accuracy.
problem Scalability issues in Bayesian neural networks.
method Collapsed inference scheme that performs Bayesian model averaging using collapsed samples.
result Significant improvements over existing methods in predictive performance and uncertainty estimation.
This work investigates how neural collapse improves transfer learning for large-scale models.
problem Improving transfer learning for large-scale models with limited labeled data.
method Investigates neural collapse and develops a fine-tuning method using skip-connections.
result Feature collapse on downstream data correlates with higher transfer accuracy.
I study Gromov-Hausdorff limits of complex curves endowed with singular flat metrics of constant diameter. I formulate a criterion that the limit is collapsed in terms of a certain piecewise affine weight function on the dual intersection complex of a semi-stable model of the degeneration introduced by Kontsevich and S…
Wide neural networks with weight decay exhibit neural collapse.
problem Proving neural collapse in wide neural networks trained with weight decay.
method Generic guarantees on neural collapse for wide networks with weight decay, proving low training error and balancedness, and bounded conditioning.
result First proof of neural collapse in end-to-end training of wide neural networks with weight decay.
Ricci flow smooths locally collapsing manifolds with controlled curvature.
problem Locally collapsing manifolds with controlled Ricci curvature.
method Ricci flow for a definite period of time, detecting collapsing infranil fiber bundles.
result Topological conditions detect collapsing infranil fiber bundles.
Stochastic variational inference for collapsed models has recently been successfully applied to large scale topic modelling. In this paper, we propose a stochastic collapsed variational inference algorithm in the sequential data setting. Our algorithm is applicable to both finite hidden Markov models and hierarchical D…
Self-attention networks localize when eigenspectrum variance is small.
problem Self-attention mechanisms can lead to rank and entropy collapses, reducing model expressivity and trainability.
method Characterized attention localization using query-key eigenspectrum variance.
result Small eigenspectrum variance prevents both rank and entropy collapses, improving model performance.
NE-VAE prevents posterior collapse in VAEs by embedding neighbors in latent space.
problem Posterior collapse in VAEs when strong decoders are used.
method Neighbor embedding in latent space to prevent collapse.
result NE-VAE produces qualitatively different latent representations with active latent dimensions.
Generative adversarial networks (GANs) often suffer from unpredictable mode-collapsing during training. We study the issue of mode collapse of Boundary Equilibrium Generative Adversarial Network (BEGAN), which is one of the state-of-the-art generative models. Despite its potential of generating high-quality images, we …
Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable recent improvements in generating realistic images, one of their major shortcomings is the fact that in practice, they tend to produce samples with little divers…
NECO detects out-of-distribution data using neural collapse properties.
problem Detecting out-of-distribution data in machine learning models.
method NECO leverages neural collapse geometric properties to identify OOD data.
result NECO achieves state-of-the-art results on OOD detection tasks.
This paper investigates how large language models achieve neural collapse, a phenomenon linked to generalization.
problem Neural collapse in large language models under imbalanced and token-rich conditions.
method Empirical investigation of scaling and regularization effects on CLMs' progression towards neural collapse.
result Neural collapse properties develop with scale and regularization, linked to generalization in language modeling.