Gradient Descent as Implicit EM in Distance-Based Neural Models

• URL: http://arxiv.org/abs/2512.24780v1
• Date: Wed, 31 Dec 2025 10:56:43 GMT
• Title: Gradient Descent as Implicit EM in Distance-Based Neural Models
• Abstract summary: Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference.<n>We provide a direct derivation to explain these phenomena.<n>No explicit inference algorithm is required because inference is embedded in optimization.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in attention mechanisms, classification heads, and energy-based models -- yet existing explanations rely on loose analogies to mixture models or post-hoc architectural interpretation. We provide a direct derivation. For any objective with log-sum-exp structure over distances or energies, the gradient with respect to each distance is exactly the negative posterior responsibility of the corresponding component: $\partial L / \partial d_j = -r_j$. This is an algebraic identity, not an approximation. The immediate consequence is that gradient descent on such objectives performs expectation-maximization implicitly -- responsibilities are not auxiliary variables to be computed but gradients to be applied. No explicit inference algorithm is required because inference is embedded in optimization. This result unifies three regimes of learning under a single mechanism: unsupervised mixture modeling, where responsibilities are fully latent; attention, where responsibilities are conditioned on queries; and cross-entropy classification, where supervision clamps responsibilities to targets. The Bayesian structure recently observed in trained transformers is not an emergent property but a necessary consequence of the objective geometry. Optimization and inference are the same process.

Related papers

• The Geometric Price of Discrete Logic: Context-driven Manifold Dynamics of Number Representations [6.414826816896125]
  Large language models (LLMs) generalize smoothly across continuous semantic spaces, yet strict logical reasoning demands the formation of discrete decision boundaries.<n>We argue that task context operates as a non-isometric dynamical operator that enforces a necessary "topological distortion"<n>We validate this geometric evolution across a gradient of tasks, from simple mapping to complex primality testing.
  arXiv  Detail & Related papers  (2026-03-24T13:41:57Z)
• OrthoFormer: Instrumental Variable Estimation in Transformer Hidden States via Neural Control Functions [0.0]
  Transformer architectures excel at sequential modeling yet remain fundamentally limited by correlational learning.<n>We propose OrthoFormer, a causally grounded architecture that embeds instrumental variable estimation directly into Transformer blocks via neural control functions.
  arXiv  Detail & Related papers  (2026-03-08T03:05:16Z)
• Distributional Equivalence in Linear Non-Gaussian Latent-Variable Cyclic Causal Models: Characterization and Learning [13.891913455492697]
  We argue that a core obstacle to a general, structural-assumption-free approach is the lack of an equivalence characterization.<n>Key to our approach is a new tool, edge rank constraints, which fills a missing piece in the toolbox for latent-variable causal discovery.
  arXiv  Detail & Related papers  (2026-03-05T03:57:14Z)
• Structural Disentanglement in Bilinear MLPs via Architectural Inductive Bias [0.0]
  We argue that failures arise from how models structure their internal representations during training.<n>We show analytically that bilinear parameterizations possess a non-mixing' property under gradient flow conditions.<n>Unlike pointwise nonlinear networks, multiplicative architectures are able to recover true operators aligned with the underlying algebraic structure.
  arXiv  Detail & Related papers  (2026-02-05T13:14:01Z)
• Deep Neural Networks as Iterated Function Systems and a Generalization Bound [2.7920304852537536]
  We show that two important deep architectures can be viewed as, or canonically associated with, place-dependent IFS.<n>We derive a Wasserstein bound for generative modeling that controls the collage-type approximation error between the data distribution and its image.
  arXiv  Detail & Related papers  (2026-01-27T07:32:49Z)
• Random-Matrix-Induced Simplicity Bias in Over-parameterized Variational Quantum Circuits [72.0643009153473]
  We show that expressive variational ansatze enter a Haar-like universality class in which both observable expectation values and parameter gradients concentrate exponentially with system size.<n>As a consequence, the hypothesis class induced by such circuits collapses with high probability to a narrow family of near-constant functions.<n>We further show that this collapse is not unavoidable: tensor-structured VQCs, including tensor-network-based and tensor-hypernetwork parameterizations, lie outside the Haar-like universality class.
  arXiv  Detail & Related papers  (2026-01-05T08:04:33Z)
• Information-Theoretic Bounds and Task-Centric Learning Complexity for Real-World Dynamic Nonlinear Systems [0.6875312133832079]
  Dynamic nonlinear systems exhibit distortions arising from coupled static and dynamic effects.<n>This paper presents a theoretical framework grounded in structured decomposition, variance analysis, and task-centric complexity bounds.
  arXiv  Detail & Related papers  (2025-09-08T12:08:02Z)
• Attention layers provably solve single-location regression [12.355792442566681]
  Attention-based models, such as Transformer, excel across various tasks but lack a comprehensive theoretical understanding, especially regarding tokenwise sparsity and internal linear structures.<n>We introduce the single-location regression task, where only one token in a sequence determines the output, and position is a latent, retrievable via a linear projection.
  arXiv  Detail & Related papers  (2024-10-02T13:28:02Z)
• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA [81.4991350761909]
  Independent component analysis (ICA) refers to an ensemble of methods which formalize this goal and provide estimation procedure for practical application. We show that the latent variables can be recovered up to a permutation if one regularizes the latent mechanisms to be sparse.
  arXiv  Detail & Related papers  (2021-07-21T14:22:14Z)
• Understanding Dynamics of Nonlinear Representation Learning and Its Application [12.697842097171119]
  We study the dynamics of implicit nonlinear representation learning. We show that the data-architecture alignment condition is sufficient for the global convergence. We derive a new training framework, which satisfies the data-architecture alignment condition without assuming it.
  arXiv  Detail & Related papers  (2021-06-28T16:31:30Z)
• Causal Expectation-Maximisation [70.45873402967297]
  We show that causal inference is NP-hard even in models characterised by polytree-shaped graphs. We introduce the causal EM algorithm to reconstruct the uncertainty about the latent variables from data about categorical manifest variables. We argue that there appears to be an unnoticed limitation to the trending idea that counterfactual bounds can often be computed without knowledge of the structural equations.
  arXiv  Detail & Related papers  (2020-11-04T10:25:13Z)
• Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
  Causal inferences can be obtained by standard algorithms for the updating of credal nets. This contribution should be regarded as a systematic approach to represent structural causal models by credal networks. Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
  arXiv  Detail & Related papers  (2020-08-02T11:19:36Z)

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.