Cross-Entropy Is All You Need To Invert the Data Generating Process

• URL: http://arxiv.org/abs/2410.21869v2
• Date: Mon, 04 Nov 2024 09:36:17 GMT
• Title: Cross-Entropy Is All You Need To Invert the Data Generating Process
• Authors: Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David Klindt,
• Abstract summary: Empirical phenomena suggest that supervised models can learn interpretable factors of variation in a linear fashion. Recent advances in self-supervised learning have shown that these methods can recover latent structures by inverting the data generating process. We prove that even in standard classification tasks, models learn representations of ground-truth factors of variation up to a linear transformation.
• Score: 29.94396019742267
• License:
• Abstract: Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neural analogy-making and the linear representation hypothesis, suggest that supervised models can learn interpretable factors of variation in a linear fashion. Recent advances in self-supervised learning, particularly nonlinear Independent Component Analysis, have shown that these methods can recover latent structures by inverting the data generating process. We extend these identifiability results to parametric instance discrimination, then show how insights transfer to the ubiquitous setting of supervised learning with cross-entropy minimization. We prove that even in standard classification tasks, models learn representations of ground-truth factors of variation up to a linear transformation. We corroborate our theoretical contribution with a series of empirical studies. First, using simulated data matching our theoretical assumptions, we demonstrate successful disentanglement of latent factors. Second, we show that on DisLib, a widely-used disentanglement benchmark, simple classification tasks recover latent structures up to linear transformations. Finally, we reveal that models trained on ImageNet encode representations that permit linear decoding of proxy factors of variation. Together, our theoretical findings and experiments offer a compelling explanation for recent observations of linear representations, such as superposition in neural networks. This work takes a significant step toward a cohesive theory that accounts for the unreasonable effectiveness of supervised deep learning.

Related papers

• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• Toward Understanding In-context vs. In-weight Learning [50.24035812301655]
  We identify simplified distributional properties that give rise to the emergence and disappearance of in-context learning. We then extend the study to a full large language model, showing how fine-tuning on various collections of natural language prompts can elicit similar in-context and in-weight learning behaviour.
  arXiv  Detail & Related papers  (2024-10-30T14:09:00Z)
• Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation [27.326817457760725]
  Invariant representation learning for unsupervised domain adaptation (UDA) has made significant advances in computer vision and pattern recognition communities. Recently, empirical connections between transferability and discriminability have received increasing attention. In this work, we systematically analyze the essentials of transferability and discriminability from the geometric perspective.
  arXiv  Detail & Related papers  (2024-06-24T13:31:08Z)
• Learning Discrete Concepts in Latent Hierarchical Models [73.01229236386148]
  Learning concepts from natural high-dimensional data holds potential in building human-aligned and interpretable machine learning models. We formalize concepts as discrete latent causal variables that are related via a hierarchical causal model. We substantiate our theoretical claims with synthetic data experiments.
  arXiv  Detail & Related papers  (2024-06-01T18:01:03Z)
• Minimum-Norm Interpolation Under Covariate Shift [14.863831433459902]
  In-distribution research on high-dimensional linear regression has led to the identification of a phenomenon known as textitbenign overfitting We prove the first non-asymptotic excess risk bounds for benignly-overfit linear interpolators in the transfer learning setting.
  arXiv  Detail & Related papers  (2024-03-31T01:41:57Z)
• Flow Factorized Representation Learning [109.51947536586677]
  We introduce a generative model which specifies a distinct set of latent probability paths that define different input transformations. We show that our model achieves higher likelihoods on standard representation learning benchmarks while simultaneously being closer to approximately equivariant models.
  arXiv  Detail & Related papers  (2023-09-22T20:15:37Z)
• A Theoretical Study of Inductive Biases in Contrastive Learning [32.98250585760665]
  We provide the first theoretical analysis of self-supervised learning that incorporates the effect of inductive biases originating from the model class. We show that when the model has limited capacity, contrastive representations would recover certain special clustering structures that are compatible with the model architecture.
  arXiv  Detail & Related papers  (2022-11-27T01:53:29Z)
• A Scaling Law for Synthetic-to-Real Transfer: A Measure of Pre-Training [52.93808218720784]
  Synthetic-to-real transfer learning is a framework in which we pre-train models with synthetically generated images and ground-truth annotations for real tasks. Although synthetic images overcome the data scarcity issue, it remains unclear how the fine-tuning performance scales with pre-trained models. We observe a simple and general scaling law that consistently describes learning curves in various tasks, models, and complexities of synthesized pre-training data.
  arXiv  Detail & Related papers  (2021-08-25T02:29:28Z)
• Gradient Starvation: A Learning Proclivity in Neural Networks [97.02382916372594]
  Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task. This work provides a theoretical explanation for the emergence of such feature imbalance in neural networks.
  arXiv  Detail & Related papers  (2020-11-18T18:52:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.