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.
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.
This paper explains why ResNets generalize better than FFNets using neural tangent kernels.
problem Understanding why deep ResNets generalize better than deep FFNets.
method Using neural tangent kernels to compare the learnability of functions induced by the kernels of ResNets and FFNets.
result The kernel of ResNets does not exhibit degeneracy as depth increases, unlike FFNets.
Bayesian methods enhance deep learning models by improving reliability and uncertainty.
problem Improving reliability and uncertainty awareness in deep learning models.
method Approximate Bayesian inference techniques, including SG-MCMC and VI, applied to deep learning models.
result Enhanced posterior inference for deep learning models, particularly in neural networks and generative models.
New kernel connects deep learning to optimization, improving generalization.
problem Understanding why deep neural networks generalize well at over-parameterization.
method Established Neural Optimization Kernel (NOK) linking deep NN to optimization problems.
result New generalization bound for deep structured approximated NOK architecture.
Study shows simple vector quantization measures correlate with deep learning generalization.
problem Understanding and predicting generalization in deep learning models.
method Applying complexity measures from approximation and information theory to deep learning features.
result Simple vector quantization measures correlate well with generalization performance in deep learning.
Survey of multimodal deep generative models for diverse data types.
problem Inference of shared representations and cross-modal generation from heterogeneous multimodal data.
method Variational autoencoders and other deep generative models.
result A comprehensive survey of multimodal deep generative models.
Framework generates personalized insulin treatment strategies using deep models.
problem Developing optimal personalized treatment strategies for diabetes patients.
method Combines deep generative time series models with decision theory.
result Demonstrated improved personalized insulin treatment strategies for diabetes patients.
Deep models generate images with missing high-frequency details.
problem Malicious use of realistic deep-generated images.
method Analysis of Fourier spectrum discrepancies between real and generated images.
result Detection method achieves up to 99.2% accuracy in classifying real and generated images.
Survey on deep models for graph generation.
problem Improving fidelity of generated graphs.
method Taxonomy and comparison of deep generative models.
result Advances in deep generative models for graph generation.
Generalization bounds derived for neural ODEs and deep residual networks.
problem Understanding the generalization capability of neural ODEs and deep residual networks.
method Lipschitz-based argument and analogy with deep residual networks.
result A generalization bound involving the magnitude of weight matrix differences.
Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving increasing attention. However, works in this area use a wide variety of tasks and e…
Generalization error defines the discriminability and the representation power of a deep model. In this work, we claim that feature space design using deep compositional function plays a significant role in generalization along with explicit and implicit regularizations. Our claims are being established with several im…
A new deep generative model uses BSDEs for high-dimensional data generation.
problem Generating high-dimensional complex data, especially images.
method Combines BSDEs with deep neural networks for training with MMD loss.
result BSDE-Gen effectively generates high-dimensional data with stochasticity.
Visualizes deep generative models for drug design.
problem Limited visualization tools for deep generative models in drug discovery.
method Proposes a visualization framework for deep graph generative models.
result Interactive visualization and molecular optimization tools.
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.
Many deep models have been recently proposed for anomaly detection. This paper presents comparison of selected generative deep models and classical anomaly detection methods on an extensive number of non--image benchmark datasets. We provide statistical comparison of the selected models, in many configurations, archite…
DeepDIG generates samples near decision boundaries of deep neural networks for better understanding.
problem Limited knowledge of how deep neural networks make decisions.
method Adversarial example generation to create samples near decision boundaries.
result Characterized decision boundaries of various deep neural network models.
Generative models improve commodity hedging using deep learning.
problem Improving risk management in commodity markets.
method Four state-of-the-art generative models adapted for commodity time series.
result Deep hedging of commodity options trained on generated time series shows promising results.
This paper presents a basic property of region dividing of ReLU (rectified linear unit) deep learning when new layers are successively added, by which two new perspectives of interpreting deep learning are given. The first is related to decision trees and forests; we construct a deep learning structure equivalent to a …
Gradient descent methods for deep ReLU networks achieve optimal generalization rates.
problem Generalization of gradient descent methods for deep neural networks
method Establishing minimax-optimal rates for GD and SGD with deep ReLU networks
result Gradient descent methods for deep ReLU networks achieve optimal generalization rates
Study compares random and learned features in deep Bayesian linear models.
problem Understanding how feature learning affects generalization in deep learning.
method Comparing deep random feature models to deep networks with trained layers.
result Random feature models can display double-descent behavior, while deep networks do not.
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.
The paper explores stability and generalization of deep GCNs.
problem Understanding the stability and generalization of deep GCNs from a theoretical perspective.
method Theoretical analysis of stability and generalization properties of deep GCNs.
result The stability and generalization of deep GCNs are influenced by the maximum absolute eigenvalue of the graph filter operators and the depth of the network.
Synthetic tabular data improves privacy while maintaining model performance.
problem Protecting privacy in synthetic data generation for machine learning.
method Deep generative models for tabular data, emphasizing privacy and model performance.
result Deep generative models enhance synthetic data generation for tabular datasets.
This review compares various deep generative models.
problem Training deep neural networks to model data distributions.
method Comprehensive comparison of VAEs, GANs, flows, energy models, and autoregressives.
result Trade-offs and interrelationships among different models.
Deep models can't generate heavy-tailed samples well.
problem Understanding the limitations of deep generative models in generating samples with heavy tails.
method Unified framework using concentration of measure and convex geometry, Gromov-Levy inequality.
result Deep generative models are not universal generators and can only produce concentrated samples with light tails.
Lecture notes on linear neural networks for deep learning optimization and generalization.
problem Understanding optimization and generalization in deep learning models.
method Mathematical tools and dynamical systems theory.
result Potential of mathematical tools to enhance understanding of deep learning.
Proposes model-based robust deep learning to handle natural variation in data.
problem Deep learning's fragility to natural variation in data.
method Develops model-based robust training algorithms using deep generative models to learn natural variation.
result Deep neural networks trained with model-based algorithms outperform standard and norm-bounded robust algorithms.
Researchers quantify the relationship between feature depth and performance in deep neural networks.
problem Understanding how depth affects feature extraction and generalization in deep neural networks.
method Adaptive analysis of feature-depth trade-offs in deep nets, proving optimal generalization performance.
result Optimal generalization performance achieved through empirical risk minimization on deep nets.
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…
Proposes a new generalization bound for Bayesian deep nets without strict assumptions.
problem Lack of generalization bounds for Bayesian deep nets without strict assumptions.
method Exploits contractivity of Log-Sobolev inequalities to add a loss-gradient norm term to the generalization bound.
result Introduces a new generalization bound for Bayesian deep nets that avoids strict assumptions.
DRMMs enable flexible conditional sampling for interactive machine learning.
problem Limited flexibility in conditional sampling for deep generative models.
method Proposes Deep Residual Mixture Models (DRMMs) that allow flexible conditional sampling.
result DRMMs enable sampling with arbitrary combinations of conditioning variables and priors.
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.
Deep Discrete Encoders (DDEs) tackle interpretable generative models for rich data with discrete latent layers.
problem Overparametrized, non-identifiable, and uninterpretable deep generative models in high-stakes applications.
method Directed graphical model with multiple binary latent layers, transparent identifiability conditions, scalable estimation pipeline.
result Transparent identifiability conditions and scalable estimation pipeline for interpretable DDEs.
Research proposes a test case generation system for deep learning models using dataset properties.
problem Automated generation of extensive test cases for deep learning models is challenging.
method Measures dataset quality and proposes a test case generation system guided by dataset properties.
result Systematic test case generation for deep learning models is effective.
New deep learning model interprets tabular data with variable selection and explainability.
problem Deep learning models lack interpretability and variable selection.
method Proposes a new network architecture that combines deep learning with generalized linear models.
result The model provides superior predictive power and interpretable results.
Refines deep generative models to improve data density precision.
problem Achieving precise representation of data probability density in deep models.
method Iterated generative modeling to refine latent space, addressing topological obstructions.
result Latent Space Refinement (LaSeR) protocol improves generative model precision.
Deep learning models have lately shown great performance in various fields such as computer vision, speech recognition, speech translation, and natural language processing. However, alongside their state-of-the-art performance, it is still generally unclear what is the source of their generalization ability. Thus, an i…
The paper analyzes how low-rank layers in neural networks improve generalization.
problem Understanding how low-rank layers affect generalization in neural networks.
method Applying Maurer's chain rule for Gaussian complexity to analyze rank and spectral norm constraints.
result Deep networks with low-rank layers achieve better generalization than those with full-rank layers.
Improved deep neural network generalization through noise resilience.
problem Understanding and predicting generalization error of deep neural networks.
method Noise resilience measures to predict generalization error.
result Secured 5th position in the PGDL competition at NeurIPS 2020.
Deep generative models parameterized by neural networks have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave the generative model unchanged b…
Deep networks generalize well due to hidden mechanisms like renormalization.
problem Generalization in deep learning networks.
method Analyzing RBMs and autoencoders, applying renormalization group principles.
result Deep networks can generalize well with fewer parameters than expected.
The paper improves deep learning generalization bounds using PAC-Bayes compression.
problem Improving generalization bounds for deep neural networks.
method Quantizing neural network parameters in a linear subspace to develop tight generalization bounds.
result Large models can be compressed significantly, explaining Occam's razor.
We present a method to generate directed acyclic graphs (DAGs) using deep reinforcement learning, specifically deep Q-learning. Generating graphs with specified structures is an important and challenging task in various application fields, however most current graph generation methods produce graphs with undirected edg…
Deep learning models are growing, posing new mathematical challenges.
problem Mathematical challenges in training, inference, generalization, and optimization of deep models.
method Formal mathematical analysis and communication with mathematicians, statisticians, and computer scientists.
result A set of new mathematical challenges in deep learning.
New research shows deep ReLU networks can be learned with polylogarithmic width.
problem Learning deep ReLU networks with limited over-parameterization.
method Using gradient descent, the study establishes learning guarantees for networks with polylogarithmic width.
result Deep ReLU networks can be learned with a polylogarithmic width condition, not just a high degree polynomial.
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.