New framework connects online learning to statistical learning for better generalization bounds.
problem Deriving generalization bounds for statistical learning algorithms.
method Constructing an online learning game and showing a connection to statistical learning.
result Established a connection between online and statistical learning, leading to new generalization bounds.
Study OOD generalization in meta-reinforcement learning using information theory.
problem Understanding how meta-reinforcement learning handles distribution shifts.
method Information-theoretic analysis of Markov Decision Processes and gradient-based algorithms.
result Established fine-grained generalization bounds for meta-reinforcement learning.
Paper tightens privacy and generalization bounds for iterative learning.
problem Balancing privacy and generalization in iterative learning algorithms.
method Established alignment between generalization and privacy, derived composition theorems for iterative algorithms.
result Generalization bounds for iterative learning algorithms are strictly tighter than existing works.
NeurIPS 2020 competition seeks to predict deep learning generalization.
problem Understanding and predicting generalization in deep learning models.
method Propose complexity measures to accurately predict generalization performance.
result A robust complexity measure could improve deep learning reliability.
New analysis improves generalization bounds for meta-learning.
problem Improving generalization in meta-learning algorithms.
method Information-theoretic analysis of MAML and its stochastic variant.
result Data-dependent generalization bound is tighter and non-vacuous.
Generative concept representations have three major advantages over discriminative ones: they can represent uncertainty, they support integration of learning and reasoning, and they are good for unsupervised and semi-supervised learning. We discuss probabilistic and generative deep learning, which generative concept re…
The paper proposes a learning algorithm that improves adaptability and generalization.
problem Improving adaptability and generalization in learning models.
method Learning to meta-learn by meta-finetuning on related tasks before adapting to specific tasks.
result Learning to meta-learn improves adaptability and generalization across various tasks.
New bounds on machine learning model generalization error moments.
problem Understanding the performance of machine learning models.
method Information-theoretic bounds on the moments of the generalization error of learning algorithms.
result Proposed bounds on generalization error moments and their high-probability bounds.
Generative data augmentation boosts learning performance in various tasks.
problem Theoretical understanding of generative data augmentation's effect.
method Established a stability bound for non-i.i.d. settings, analyzed Gaussian mixture models and generative adversarial nets.
result Generative data augmentation can improve learning guarantees, especially in small train sets.
Automatically generates a deep RL curriculum for faster and more stable learning.
problem How to automatically generate a curriculum for deep RL agents.
method Interprets curriculum generation as an inference problem, learning task distributions progressively.
result Curricula significantly improve learning performance across various environments and deep RL algorithms.
New approach for large-scale distributed learning systems that improve generalization performance.
problem Transitioning from centralized to distributed AI systems for complex learning tasks.
method Self-organizing hierarchical structuring mechanism based on agglomerative clustering, hierarchical generalization, and personalized learning.
result Demonstrates better generalization performance compared to conventional federated learning algorithms.
SALR improves deep learning generalization by dynamically adjusting learning rates.
problem Improving generalization in deep learning models.
method Sharpness-aware learning rate scheduling based on local loss function sharpness.
result SALR drives solutions to flatter regions, improving generalization and convergence.
"Deep Learning" methods attempt to learn generic features in an unsupervised fashion from a large unlabelled data set. These generic features should perform as well as the best hand crafted features for any learning problem that makes use of this data. We provide a definition of generic features, characterize when it i…
This paper tackles optimizee generalization in L2O, improving generalization on various models.
problem L2O methods often struggle with optimizee generalization, leading to poor performance on unseen data.
method The paper introduces flatness-aware regularizers based on local entropy and Hessian to improve optimizee generalization.
result The proposed method significantly improves generalization performance on multiple sophisticated L2O models and diverse optimizees.
Study on meta-reinforcement learning generalization in high-dimensional tasks.
problem Generalization performance of meta-reinforcement learning algorithms in high-dimensional tasks.
method High-dimensional, procedurally generated environments.
result Meta-reinforcement learning algorithms exhibit strong overfitting on challenging tasks.
This paper analyzes how diffusion models learn and generalize concepts.
problem Learning and generalizing concepts in compositional data-generating processes.
method Introduced a structured identity mapping (SIM) task to analyze neural network learning dynamics.
result SIM task captures key empirical observations on compositional generalization.
A new method for continual learning in GANs learns new modes with limited data.
problem Learning new target modes with limited samples while preserving previously learned ones.
method Mode-affinity score for generative modeling, generator replay, and weighted label generation.
result Gains over state-of-the-art methods, even with fewer training samples.
TGLS generates text by optimizing search results and learning from them.
problem Unsupervised text generation without explicit training data.
method TGLS uses simulated annealing to estimate sentence quality, then a conditional generative model learns from search results.
result TGLS outperforms unsupervised baselines and matches state-of-the-art supervised methods in paraphrase generation.
This paper analyzes generalization issues in deep reinforcement learning.
problem Understanding and improving generalization capabilities of deep reinforcement learning policies.
method Formalizing and categorizing solutions to address overfitting in deep reinforcement learning.
result A comprehensive analysis of generalization challenges and solutions in deep reinforcement learning.
FeAT improves OOD generalization by learning richer features.
problem Improving feature learning for out-of-distribution (OOD) generalization.
method Feature Augmented Training (FeAT) iteratively augments and retains features from different subsets of training data.
result FeAT effectively learns richer features, boosting OOD performance.
Scalable Bayesian sampling is playing an important role in modern machine learning, especially in the fast-developed unsupervised-(deep)-learning models. While tremendous progresses have been achieved via scalable Bayesian sampling such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD)…
User smeznar achieved 8th place in PGDL by predicting generalization of deep learning models.
problem Understanding and predicting generalization in deep learning models.
method Creating simple metrics and finding their best combination for automatic testing on a dataset.
result Combination of various properties of neural network architectures can be used for generalization prediction.
APT-Gen generates tasks to help RL learn in hard problems.
problem Learning in hard exploration problems.
method APT-Gen uses a task generator to create tasks from a parameterized space, balancing performance and similarity to target tasks.
result APT-Gen outperforms baselines in grid world and robotic manipulation tasks.
Generative model learns vehicle trajectory distributions for better data generalization.
problem Data sparsity and privacy issues in urban vehicle trajectory analysis.
method Generative adversarial imitation learning framework for urban vehicle trajectory generation.
result TrajGAIL model produces synthetic trajectories similar to real ones, achieving significant performance gains.
Generative neural nets learn deep policies conditioned on goals.
problem Learning optimal policies for specific goals in reinforcement learning.
method Goal-conditioned neural nets that generate deep neural policies.
result Single learned policy generator can achieve any desired return.
Deep learning models optimize protein sequences.
problem Optimizing protein properties through sequence design.
method Deep generative models guided by machine learning.
result Improved protein sequence generation from prior knowledge.
New method improves reinforcement learning generalization.
problem Few environments lead to poor generalization in reinforcement learning.
method Integrates sequential structure into representation learning, using a policy similarity metric (PSM) and contrastive embeddings (PSEs).
result PSEs improve generalization across various benchmarks.
New measure quantifies task difficulty for machine learning models.
problem Quantifying the inherent difficulty of machine learning tasks.
method Inductive bias complexity measure.
result Tasks requiring generalization over many dimensions are more difficult.
Paper develops a fractal dimension-based generalization measure.
problem Developing a robust generalization measure for machine learning models.
method Analyzes decision boundaries using fractal dimension concept.
result Developed a generalization measure based on fractal dimension.
Paper proposes a math-inspired L2O model for better generalization.
problem Overfitting and poor generalization of generic L2O models.
method Derived mathematical conditions for successful update rules and proposed a novel L2O model.
result Proposed model outperforms generic L2O models in out-of-distribution settings.
Advances in neural network based classifiers have transformed automatic feature learning from a pipe dream of stronger AI to a routine and expected property of practical systems. Since the emergence of AlexNet every winning submission of the ImageNet challenge has employed end-to-end representation learning, and due to…
Machine learning-based lithography hotspot detection has been deeply studied recently, from varies feature extraction techniques to efficient learning models. It has been observed that such machine learning-based frameworks are providing satisfactory metal layer hotspot prediction results on known public metal layer be…
Faster ZSL with continual learning and self-gating.
problem Generalizing models to unseen categories and handling sequential data.
method Meta-continual zero-shot learning (MCZSL) with self-gating and scaled class normalization.
result Outperforms state-of-the-art results with faster training (>100imes). Autoencoders are widely used for unsupervised learning and as a regularization scheme in semi-supervised learning. However, theoretical understanding of their generalization properties and of the manner in which they can assist supervised learning has been lacking. We utilize recent advances in the theory of deep learn…
Deep reinforcement learning algorithms have shown an impressive ability to learn complex control policies in high-dimensional tasks. However, despite the ever-increasing performance on popular benchmarks, policies learned by deep reinforcement learning algorithms can struggle to generalize when evaluated in remarkably …
A new method generates meta-tasks using generative models for unsupervised learning.
problem Creating synthetic meta-tasks for unsupervised learning.
method Generative models with latent space interpolation for sampling.
result The method outperforms or is competitive with baselines on few-shot classification tasks.
We establish conditions for compositional generalization in machine learning.
problem Achieving compositional generalization in machine learning models.
method We reformulate compositionality as a property of the data-generating process and derive mild conditions on the training distribution and model architecture.
result Our theoretical framework enables compositional generalization under mild conditions.
Learning rate annealing helps even in convex problems, improving generalization.
problem Improving generalization in neural networks, especially convex problems.
method Learning rate annealing schedule (large initial, then small learning rate).
result Gradient descent can reach minima with better generalization using learning rate annealing.
A new method removes policy optimization in adversarial imitation learning.
problem Adversarial imitation learning's delicate alternated optimization.
method Explicitly condition discriminator on two policies, solving generator's optimization problem directly.
result Simpler approach competitive to prevalent methods.
Transformers learn to solve various tasks without explicit design.
problem Training models with minimal inductive bias.
method Meta-learning approach to train general-purpose in-context learning algorithms.
result Transformers can be meta-trained to solve a wide range of tasks.
PhyloVAE learns tree topologies without supervision.
problem Learning accurate tree representations from evolutionary data.
method Unsupervised learning via variational autoencoders with efficient tree generation.
result PhyloVAE generates high-resolution tree topologies efficiently.
The study assesses machine learning generalization using various data set characteristics.
problem Estimating confidence in machine learning predictions and assessing generalization capabilities.
method Meta-analysis of 109 classification data sets, modeling generalization as a function of various characteristics.
result The convex hull of the training data is relevant for assessing machine learning generalization, challenging the common assumption about the curse of dimensionality.
Generative Neuro-Symbolic model learns from raw data with rich conceptual representations.
problem Learning rich, general-purpose conceptual representations from raw perceptual inputs.
method Generative Neuro-Symbolic (GNS) model combining symbolic and neural network approaches.
result Model learns from raw data and generalizes to 4 unique tasks.
New method generates universal adversarial perturbations across different image sources.
problem Certifying robustness of deep learning models with universal adversarial perturbations across various image sources.
method Few-shot learning approach using bilevel optimization and learning-to-optimize techniques.
result Improved attack success rate and faster performance compared to existing methods.
This paper analyzes the stability and generalization of triplet learning algorithms.
problem Lack of theoretical understanding of triplet learning's generalization performance.
method Stability analysis and high-probability generalization bounds for triplet learning algorithms.
result Established general high-probability generalization bound for triplet learning algorithms.
Paper tackles reinforcement learning generalization through invariant policy optimization.
problem Learning policies that generalize beyond training domains.
method Invariant policy optimization principle and novel learning algorithm IPO.
result Significant improvements in generalization performance on unseen domains.
GGAN improves audio representation learning with fewer labels.
problem Learning representations for specific tasks from unlabelled data.
method Guided Generative Adversarial Neural Network (GGAN).
result GGAN learns better representations with fewer labelled data.
This work fills the gap in understanding multi-objective learning generalization.
problem Lack of statistical learning theory insights into multi-objective learning generalization.
method Established generalization bounds and excess bounds for multi-objective learning.
result Showed that all Pareto-optimal solutions can be approximated by empirically Pareto-optimal ones, but not vice versa.