Analyzing the Role of Permutation Invariance in Linear Mode Connectivity

• URL: http://arxiv.org/abs/2503.06001v2
• Date: Wed, 12 Mar 2025 16:22:51 GMT
• Title: Analyzing the Role of Permutation Invariance in Linear Mode Connectivity
• Authors: Keyao Zhan, Puheng Li, Lei Wu,
• Abstract summary: We show that as the student network width $m$ increases, the LMC loss barrier modulo permutation exhibits a double descent behavior.<n>We observe a sharp transition in the sparsity of GD/SGD solutions when increasing the learning rate and investigate how this sparsity preference affects the LMC loss barrier modulo permutation.
• Score: 4.516746821973374
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: It was empirically observed in Entezari et al. (2021) that when accounting for the permutation invariance of neural networks, there is likely no loss barrier along the linear interpolation between two SGD solutions -- a phenomenon known as linear mode connectivity (LMC) modulo permutation. This phenomenon has sparked significant attention due to both its theoretical interest and practical relevance in applications such as model merging. In this paper, we provide a fine-grained analysis of this phenomenon for two-layer ReLU networks under a teacher-student setup. We show that as the student network width $m$ increases, the LMC loss barrier modulo permutation exhibits a double descent behavior. Particularly, when $m$ is sufficiently large, the barrier decreases to zero at a rate $O(m^{-1/2})$. Notably, this rate does not suffer from the curse of dimensionality and demonstrates how substantial permutation can reduce the LMC loss barrier. Moreover, we observe a sharp transition in the sparsity of GD/SGD solutions when increasing the learning rate and investigate how this sparsity preference affects the LMC loss barrier modulo permutation. Experiments on both synthetic and MNIST datasets corroborate our theoretical predictions and reveal a similar trend for more complex network architectures.

Related papers

• Optimization and generalization analysis for two-layer physics-informed neural networks without over-parametrization [0.6215404942415159]
  This work focuses on the behavior of gradient descent (SGD) in solving least-squares regression with physics-informed neural networks (PINNs)<n>We show that if the network width exceeds a threshold that depends only on $epsilon$ and the problem, then the training loss and expected loss will decrease below $O(epsilon)$.
  arXiv  Detail & Related papers  (2025-07-22T09:24:22Z)
• Universal Response and Emergence of Induction in LLMs [0.0]
  We study the emergence of induction behavior within LLMs by probing their response to weak single-token perturbations of the residual stream. We find that LLMs exhibit a robust, universal regime in which their response remains scale-invariant under changes in perturbation strength. Our results provide insights into the collective interplay of components within LLMs and serve as a benchmark for large-scale circuit analysis.
  arXiv  Detail & Related papers  (2024-11-11T15:47:15Z)
• Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers [54.20763128054692]
  We study how a two-attention-layer transformer is trained to perform ICL on $n$-gram Markov chain data. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model.
  arXiv  Detail & Related papers  (2024-09-09T18:10:26Z)
• Landscaping Linear Mode Connectivity [76.39694196535996]
  linear mode connectivity (LMC) has garnered interest from both theoretical and practical fronts. We take a step towards understanding it by providing a model of how the loss landscape needs to behave topographically for LMC.
  arXiv  Detail & Related papers  (2024-06-24T03:53:30Z)
• GD doesn't make the cut: Three ways that non-differentiability affects neural network training [5.439020425819001]
  This paper critically examines the distinctions between methods applied to non-differentiable functions (NGDMs) and classical gradient descents (GDs) for differentiable functions. Our work identifies critical misunderstandings of algorithms in influential literature, stemming from an overreliance on strong assumptions.
  arXiv  Detail & Related papers  (2024-01-16T15:11:29Z)
• Learning Discretized Neural Networks under Ricci Flow [48.47315844022283]
  We study Discretized Neural Networks (DNNs) composed of low-precision weights and activations.<n>DNNs suffer from either infinite or zero gradients due to the non-differentiable discrete function during training.
  arXiv  Detail & Related papers  (2023-02-07T10:51:53Z)
• Training invariances and the low-rank phenomenon: beyond linear networks [44.02161831977037]
  We show that when one trains a deep linear network with logistic or exponential loss on linearly separable data, the weights converge to rank-$1$ matrices. This is the first time a low-rank phenomenon is proven rigorously for nonlinear ReLU-activated feedforward networks. Our proof relies on a specific decomposition of the network into a multilinear function and another ReLU network whose weights are constant under a certain parameter directional convergence.
  arXiv  Detail & Related papers  (2022-01-28T07:31:19Z)
• Multi-scale Feature Learning Dynamics: Insights for Double Descent [71.91871020059857]
  We study the phenomenon of "double descent" of the generalization error. We find that double descent can be attributed to distinct features being learned at different scales.
  arXiv  Detail & Related papers  (2021-12-06T18:17:08Z)
• Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks [83.58049517083138]
  We consider a two-layer ReLU network trained via gradient descent. We show that SGD is biased towards a simple solution. We also provide empirical evidence that knots at locations distinct from the data points might occur.
  arXiv  Detail & Related papers  (2021-11-03T15:14:20Z)
• The edge of chaos: quantum field theory and deep neural networks [0.0]
  We explicitly construct the quantum field theory corresponding to a general class of deep neural networks. We compute the loop corrections to the correlation function in a perturbative expansion in the ratio of depth $T$ to width $N$. Our analysis provides a first-principles approach to the rapidly emerging NN-QFT correspondence, and opens several interesting avenues to the study of criticality in deep neural networks.
  arXiv  Detail & Related papers  (2021-09-27T18:00:00Z)
• Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off [10.182922771556742]
  We present a nonasymptotic generalization theory for two-layer neural networks with ReLU activation function. We show that overparametrized random feature models suffer from the curse of dimensionality and thus are suboptimal.
  arXiv  Detail & Related papers  (2021-06-09T03:52:18Z)
• Understanding Self-supervised Learning with Dual Deep Networks [74.92916579635336]
  We propose a novel framework to understand contrastive self-supervised learning (SSL) methods that employ dual pairs of deep ReLU networks. We prove that in each SGD update of SimCLR with various loss functions, the weights at each layer are updated by a emphcovariance operator. To further study what role the covariance operator plays and which features are learned in such a process, we model data generation and augmentation processes through a emphhierarchical latent tree model (HLTM)
  arXiv  Detail & Related papers  (2020-10-01T17:51:49Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)
• The Implicit Bias of Gradient Descent on Separable Data [44.98410310356165]
  We show the predictor converges to the direction of the max-margin (hard margin SVM) solution. This can help explain the benefit of continuing to optimize the logistic or cross-entropy loss even after the training error is zero.
  arXiv  Detail & Related papers  (2017-10-27T21:47:58Z)

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.