Consistency distillation reduces memorization in diffusion models without harming sample quality.
problem Understanding how distillation affects memorization in diffusion models.
method Analysis of consistency distillation in diffusion models using a random feature neural network model.
result Consistency distillation reduces memorization in diffusion models without harming sample quality.
Study on recurrent neural networks' feature selection and memorization using F1B test.
problem Conflict between feature selection and memorization in sequence learning.
method Flagged-1-Bit (F1B) test, four recurrent network models studied analytically and experimentally.
result Conflict can be resolved by gating mechanism or increasing state dimension.
The paper analyzes how deep models memorize spurious features.
problem Understanding how deep models memorize spurious features in training data.
method Characterizes spurious feature memorization via model stability and feature alignment.
result Memorization of spurious features weakens as generalization capability increases.
Memorizing rare examples helps neural networks generalize better.
problem Improving generalization in deep learning models.
method Theoretical analysis and experiments on neural networks with composition capability.
result Memorizing rare examples can help neural networks make correct predictions on rare test examples.
A new model improves recurrent neural networks' ability to memorize long sequences.
problem Improving recurrent neural networks' ability to memorize long sequences and extract task-relevant features.
method Proposes a Linear Memory Network with an encoding-based memorization component and a specialized training algorithm.
result Improves the final performance of recurrent neural networks when memorizing long sequences is necessary.
Deep networks preferentially learn shared features, avoiding memorization in early layers.
problem Understanding how deep neural networks generalize vs. memorize training data.
method Replica-based mean field geometric analysis of deep neural networks.
result Deep layers predominantly memorize, while early layers are minimally affected.
Generative diffusion models gradually memorize training data, losing independent dimensions.
problem Understanding how generative diffusion models memorize training data, especially on low-dimensional manifolds.
method Measuring latent dimensionality via the learned score field, proposing a geometric memorization theory.
result Generative diffusion models experience a smooth collapse of their capacity to vary across independent directions as data become scarce, leading to near point-wise replication of salient features.
LEC prevents deep nets from memorizing noisy examples.
problem Deep nets overfit to noisy data.
method LEC removes noisy examples based on an ensemble of perturbed networks.
result LTEC outperforms state-of-the-art on noisy MNIST, CIFAR-10, and CIFAR-100.
Diffusion models generalize well until a threshold is reached, preventing memorization.
problem Understanding why diffusion models don't memorize training data.
method Investigation of training dynamics and two timescales: τ g e n τ_\mathrm{gen} τ gen and τ m e m τ_\mathrm{mem} τ mem . result The threshold τ m e m τ_\mathrm{mem} τ mem increases linearly with training set size n n n , preventing memorization. This study reveals fundamental trade-offs between memorization and robustness in neural networks.
problem Understanding the balance between memorization and robustness in neural networks.
method Analyzes two-layer neural networks in various high-dimensional linearized regimes, focusing on Sobolev-seminorm.
result Establishes fundamental trade-offs between memorization and robustness, with lower bounds on Sobolev-seminorm.
The roles played by learning and memorization represent an important topic in deep learning research. Recent work on this subject has shown that the optimization behavior of DNNs trained on shuffled labels is qualitatively different from DNNs trained with real labels. Here, we propose a novel permutation approach that …
The study examines how the number of noise samples affects diffusion models' performance.
problem Understanding the balance between generalization and memorization in diffusion models.
method Theoretical analysis and empirical experiments with Denoising Score Matching (DSM) using random features.
result Precise expressions for test and train errors under specific conditions reveal the mechanisms of generalization and memorization.
Study flaws in generative model evaluation metrics, especially for diffusion models.
problem Flaws in existing metrics for evaluating generative models, particularly for diffusion models.
method Systematic study of generative models, human perception experiments, and analysis of feature extractors.
result State-of-the-art perceptual realism of diffusion models is not reflected in commonly reported metrics.
Analyzes how class imbalance and heterogeneity affect diffusion model learning dynamics.
problem Understanding how class imbalance and heterogeneity impact the learning dynamics of diffusion models.
method Developed a high-dimensional analytical framework to study class-dependent learning in score-based diffusion models.
result Class variance is the primary determinant of learning order, favoring higher-variance classes; centroid geometry plays a secondary role.
Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature transformations are effective and interpretable, while generalization requires more…
Neural networks memorize exceptions, leading to poor generalization.
problem Memorization of exceptions hinders neural network generalization.
method Formalized memorization-generalization interplay, proposed MAT to shift logits.
result MAT improves generalization by learning robust patterns invariant across distributions.
Local data coverage governs memorization in diffusion models.
problem Memorization in diffusion models
method Derive a theoretical criterion based on local data coverage
result Predicts memorization based on density of training data in neighborhood and dataset size
Geometric framework explains memorization in generative models.
problem Memorization in generative models raises legal and privacy concerns.
method Manifold memorization hypothesis (MMH) using manifold geometry.
result Formalizes and categorizes memorization into overfitting and distribution-driven types.
The paper identifies patterns in language model weights used for memorizing paragraphs.
problem Locating the specific mechanisms and weights used by language models to memorize paragraphs.
method Examined gradients and attention patterns in language models to identify memorized paragraphs.
result Gradients of memorized paragraphs have a distinguishable spatial pattern, and localized attention heads are involved in paragraph memorization.
Study shows how deep generative models can memorize data.
problem Understanding and preventing memorization in deep generative models.
method Adapted a memorization measure for unsupervised density estimation and demonstrated its effectiveness.
result Memorization in deep generative models differs from mode collapse and overfitting.
Paper proposes efficient BNN inference flow to reduce computation and memory costs.
problem High computation complexity in Bayesian Neural Networks (BNNs) limits deployment in power-constrained systems.
method Feature decomposition and memorization strategy to reduce computations and a memory-friendly computing framework to reduce memory overhead.
result Reduces computation by about half and energy consumption by 73% with 14% area overhead.
We study finite sample expressivity, i.e., memorization power of ReLU networks. Recent results require N N N hidden nodes to memorize/interpolate arbitrary N N N data points. In contrast, by exploiting depth, we show that 3-layer ReLU networks with Ω ( N ) Ω(\sqrt{N}) Ω ( N ) hidden nodes can perfectly memorize most datasets with N N N po…
Optimal ReLU networks can memorize any separable set of points with a small number of parameters.
problem The optimal number of parameters required to memorize a set of points using ReLU networks.
method Construction of ReLU networks with specific bit complexity to memorize points satisfying a mild separability assumption.
result Optimal ReLU networks can memorize any separable set of points with a number of parameters that is i l d e O ( N ) ilde{O}(\sqrt{N}) i l d e O ( N ) . LLMs can memorize economic data and recall exact values before their training cutoff.
problem Evaluating the trustworthiness of LLMs' economic forecasts during their training period.
method Demonstrated through counterfactual forecasting and analysis of LLMs' recall ability.
result LLMs have memorized economic and financial data, leading to recall-level accuracy before their knowledge cutoff.
New method reduces memorization in diffusion models without sacrificing image quality.
problem Diffusion models often memorize training data, especially with small datasets.
method Train models using noisy data at large noise scales to reduce memorization.
result Significant reduction in memorization without compromising image quality.
Logarithmic network width suffices for robust memorization.
problem Achieving robust memorization in neural networks.
method Established upper and lower bounds on robust memorization radius.
result Width logarithmic in the number of samples is necessary and sufficient for robust memorization.
New approach shows data memorization trade-offs in large models.
problem Data memorization in large language models and its privacy implications.
method Developed a new approach using strong data processing inequalities to prove lower bounds on memorization.
result Proved that Ω ( d ) Ω(d) Ω ( d ) bits of training data information must be memorized for O ( 1 ) O(1) O ( 1 ) examples, decaying with example growth. Study compares memorization of SimCLR to supervised and random labels training.
problem Understanding memorization in contrastive learning.
method Investigated SimCLR's memorization properties compared to supervised and random labels training.
result SimCLR's memorization is similar to random labels training in terms of training object complexity distribution.
Deep networks can memorize random labels; symmetric loss improves this.
problem Deep networks can memorize random labels, ignoring standard regularization.
method Empirical studies with MNIST and CIFAR-10 datasets, formal definition of robustness.
result Symmetric loss function improves network's ability to resist memorization.
Learning requires memorizing labels, especially in long-tailed data.
problem Understanding why memorizing labels is necessary for accurate learning.
method Introduced a theoretical model for natural data distributions, showing memorization is necessary for optimal generalization error.
result Memorization of labels, even for outliers and noisy labels, is necessary for achieving close-to-optimal generalization error.
This paper explores memorization in adversarial training and proposes a mitigation algorithm.
problem Understanding and mitigating robust overfitting in adversarial training.
method Demonstrated the capacity of deep networks to memorize adversarial examples, analyzed convergence and generalization issues, and proposed a new mitigation algorithm.
result Identified robust overfitting as a significant drawback of adversarial training and proposed a mitigation algorithm.
Study shows FL reduces unintended memorization by clustering data and using strong user-level privacy.
problem Unintended memorization in federated learning.
method Examined the effect of clustering data and using strong user-level differential privacy in FL.
result Clustering data and strong user-level differential privacy reduce unintended memorization.
ResMem improves model generalization by explicitly memorizing residuals.
problem Improving model generalization in neural networks.
method ResMem algorithm that augments a model with a k-nearest neighbor based regressor fitted to residuals.
result ResMem consistently improves test set generalization across various benchmarks.
Diffusion models can memorize training data, limiting their creativity and privacy.
problem Memorization in diffusion models that reproduces training data instead of generating novel outputs.
method Dual-separation approach via statistical estimation and network approximation.
result Pruning-based method reduces memorization while maintaining generation quality.
RAF model explains neural networks' dual rule learning and fact memorization.
problem Understanding how neural networks learn rules and memorize facts simultaneously.
method Introduces the Rules-and-Facts (RAF) model to bridge generalization and memorization.
result Characterizes conditions for simultaneous rule learning and fact memorization in neural networks.
Introduces Relational Privacy (RP) to control relation memorization in question answering models.
problem Relation memorization in question answering models can lead to privacy issues.
method Formalizes Relational Privacy (RP) and Differential Relational Privacy (DrP), providing bounds on relation memorization.
result DrP allows effective learning of general properties of underlying concepts while preventing relation memorization.
Gradient descent memorizes many Gaussians efficiently.
problem Memorizing many Gaussians with minimal parameters.
method Gradient descent on a depth-two neural network.
result One step of gradient descent memorizes $Ω\left(\frac{dq}{\log^4(d)}
ight)$ Gaussians.
The bias potential model explains how generative models can generalize or memorize samples.
problem Understanding and achieving generalization in generative models like GANs.
method Introducing the bias potential model to analyze the behavior of generative models.
result Dimension-independent generalization accuracy can be achieved with early stopping in the bias potential model.
The study uncovers the conditions under which diffusion models memorize or generalize.
problem Understanding the balance between memorization and generalization in diffusion models.
method Theoretical and mathematical framework to investigate memorization and generalization in diffusion models.
result Theoretical crossover point predicts a phase transition in diffusion models, validating the hypothesis.
Neural networks can memorize random labels just as well as true labels.
problem Understanding how neural networks memorize random labels.
method Empirical experiments and similarity measurement of learned patterns.
result DNNs have a 'One way to Learn' but 'N ways to Memorize'.
Deep models memorize training data in geophysical inversion, leading to biased posterior distributions.
problem Memorization of training data biases learned priors in geophysical inverse problems.
method Casting generative models' training as maximum likelihood, we show memorization results in a reweighted empirical distribution for diffusion models, leading to Gaussian mixture priors and posteriors.
result Memorization leads to posterior distributions that are likelihood-weighted lookup among stored training examples, affecting full waveform inversion outcomes.
Deep neural networks can memorize training data even with just a few more parameters than samples.
problem Deep neural networks memorizing training data in mildly overparametrized regimes.
method Training neural networks with a number of parameters just a constant factor more than training samples.
result Neural networks can achieve 100% accuracy on training data in mildly overparametrized regimes.
Passenger Name Records (PNRs) are at the heart of the travel industry. Created when an itinerary is booked, they contain travel and passenger information. It is usual for airlines and other actors in the industry to inter-exchange and access each other's PNR, creating the challenge of using them without infringing data…
New training method for ReLU networks achieves optimal weight size for memorization.
problem Approximate memorization of arbitrary real labels with neural networks.
method Complex recombination training procedure for ReLU networks.
result Approximate memorization with nearly optimal weight size and neuron count.
Large learning rates prevent memorization in denoising score matching.
problem Memorization of training data in diffusion-based generative models.
method Investigating the role of large learning rates in the small-noise regime, proving that they prevent convergence to the empirical optimal score.
result Large learning rates prevent memorization by making it impossible for the learned score to be arbitrarily close to the empirical optimal score.
Transformers with CoT don't enhance reasoning power across all tasks.
problem Does CoT enhance the reasoning power of transformers?
method Examined the memorization capabilities of fixed-precision transformers with and without CoT.
result Transformers with CoT cannot memorize all reasoning tasks, leading to a negative answer.
Study interprets neural network generalization and memorization on corrupted data.
problem Understanding when a neural network has memorized corrupted data versus learned the underlying rule.
method Analyzes multi-layer perceptrons and Transformers on modular arithmetic tasks with corrupted labels.
result Regularization methods can force networks to ignore corrupted data, improving accuracy on uncorrupted data.
Early stopping improves generalization in overparameterized diffusion models.
problem Understanding and optimizing generalization in overparameterized diffusion models.
method Revisiting diffusion models, showing generalization occurs before memorization, and developing a phase diagram.
result Generalization time scales with dataset size, supporting early-stopping criteria.