paper-with-me

홈 › Papers

Bias and Generalization in Deep Generative Models: An Empirical Study

2018-11-08 · NeurIPS 2018 12 · Shengjia Zhao, Hongyu Ren, Arianna Yuan, Jiaming Song, Noah Goodman, Stefano Ermon

In high dimensional settings, density estimation algorithms rely crucially on their inductive bias. Despite recent empirical success, the inductive bias of deep generative models is not well understood. In this paper we propose a framework to systematically investigate bias and generalization in deep generative models of images. Inspired by experimental methods from cognitive psychology, we probe each learning algorithm with carefully designed training datasets to characterize when and how existing models generate novel attributes and their combinations. We identify similarities to human psychology and verify that these patterns are consistent across commonly used models and architectures.

📄 PDF Abstract BibTeX arXiv:1811.03259

Code (2)

ermongroup/BiasAndGeneralization 공식 구현 tf
rakhimovv/GenerativeLatentFlow pytorch

Tasks

Density EstimationInductive Bias

Similar Papers 제목 키워드 기반

Is Generation Required for Data-Efficient Perception?

2025-12-09 · Jack Brady, Bernhard Schölkopf, Thomas Kipf, Simon Buchholz 외 arxiv

It has been hypothesized that achieving the data efficiency of human visual perception requires a generative approach in which internal representations result from inverting a decoder. Yet today's most successful vision …

Generalization and Memorization: The Bias Potential Model

2020-11-29 · Hongkang Yang, Weinan E

Models for learning probability distributions such as generative models and density estimators behave quite differently from models for learning functions. One example is found in the memorization phenomenon, namely the …

Memorizationmodel

The Price of Implicit Bias in Adversarially Robust Generalization

2024-06-07 · Nikolaos Tsilivis, Natalie Frank, Nathan Srebro, Julia Kempe

We study the implicit bias of optimization in robust empirical risk minimization (robust ERM) and its connection with robust generalization. In classification settings under adversarial perturbations with linear models, …

Why are Sensitive Functions Hard for Transformers?

2024-02-15 · Michael Hahn, Mark Rofin

Empirical studies have identified a range of learnability biases and limitations of transformers, such as a persistent difficulty in learning to compute simple formal languages such as PARITY, and a bias towards low-degr…

Sensitivity

Towards Better Generalization: Weight Decay Induces Low-rank Bias for Neural Networks

2024-10-03 · Ke Chen, Chugang Yi, Haizhao Yang

We study the implicit bias towards low-rank weight matrices when training neural networks (NN) with Weight Decay (WD). We prove that when a ReLU NN is sufficiently trained with Stochastic Gradient Descent (SGD) and WD, i…