Fast Generalization after Interpolation via Critically Damped Momentum Optimization

• URL: http://arxiv.org/abs/2606.01521v1
• Date: Mon, 01 Jun 2026 00:54:45 GMT
• Title: Fast Generalization after Interpolation via Critically Damped Momentum Optimization
• Abstract summary: We show that GROKtimizer offers a natural solution for selecting low-norm interpolating solutions.<n> GROKtimizer provides a quadratic speedup over classical gradient descent, with provable optimality among first-order generalizations.<n>We reconcile our findings with the flat-minima hypothesis, highlighting the importance of post-interpolation dynamics in the construction of high-quality, generalizing models.
• Score: 44.00737032715565
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A central problem in machine learning is that models can achieve near-perfect training performance while generalizing substantially less well to unseen examples. This gap is especially acute in high-dimensional, low-sample regimes, where many interpolating solutions exist and optimization must implicitly select among minima with different generalization properties. Following recent theoretical advances on optimization dynamics near the interpolation threshold, we note that the two-regime structure of risk minimization, with loss minimization followed by complexity minimization, motivates a biphasic optimization schedule. We thus theoretically demonstrate that GROKtimizer, a biphasic strategy that combines rapid convergence to interpolation with Critically Damped Momentum (CDM)-based post-interpolation norm minimization, offers a natural solution for selecting low-norm interpolating solutions. Under a local quadratic model of the post-interpolation basin, GROKtimizer provides a quadratic speedup over classical gradient descent, with provable optimality among first-order optimizers. To showcase the applicability of our method, we evaluate GROKtimizer on several synthetic benchmarks common in the classical grokking literature and on various real-world datasets. Finally, we reconcile our findings with the flat-minima hypothesis, highlighting the importance of post-interpolation dynamics in the construction of high-quality, generalizing models.

Related papers

• Binary Optimization with Complex Constraints via Quantum Approximate Multi-Objective Optimization [1.3827807729367585]
  We show that a class of binary optimization problems with complex non-quadratic objectives or constraints can be reformulated as multi-objective quadratic unconstrained binary optimization problems.<n>We demonstrate the approach for binary portfolio optimization under a Conditional Value-at-Risk constraint.
  arXiv  Detail & Related papers  (2026-09-12T08:07:15Z)
• Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization [66.08522228989634]
  We establish the first global convergence result of neural networks for two stage least squares (2SLS) approach in nonparametric instrumental variable regression (NPIV)<n>This is achieved by adopting a lifted perspective through mean-field Langevin dynamics (MFLD)
  arXiv  Detail & Related papers  (2025-11-18T17:51:17Z)
• Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates [23.143960802555714]
  We study bilevel optimization, in which one optimization problem is nested inside another.<n>Motivated by concerns about individual privacy, we develop novel bilevel algorithms.<n>Our bounds do not depend on the focus of the inner problem.
  arXiv  Detail & Related papers  (2025-06-15T23:21:36Z)
• Scalable Min-Max Optimization via Primal-Dual Exact Pareto Optimization [66.51747366239299]
  We propose a smooth variant of the min-max problem based on the augmented Lagrangian.<n>The proposed algorithm scales better with the number of objectives than subgradient-based strategies.
  arXiv  Detail & Related papers  (2025-03-16T11:05:51Z)
• Low-Rank Extragradient Methods for Scalable Semidefinite Optimization [17.384717824118255]
  We focus on high-dimensional and plausible settings in which the problem admits a low-rank solution.<n>We provide several theoretical results proving that, under these circumstances, the well-known Extragradient method converges to a solution of the constrained optimization problem.
  arXiv  Detail & Related papers  (2024-02-14T10:48:00Z)
• Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization [108.35402316802765]
  We propose a new first-order optimization algorithm -- AcceleratedGradient-OptimisticGradient (AG-OG) Ascent. We show that AG-OG achieves the optimal convergence rate (up to a constant) for a variety of settings. We extend our algorithm to extend the setting and achieve the optimal convergence rate in both bi-SC-SC and bi-C-SC settings.
  arXiv  Detail & Related papers  (2022-10-31T17:59:29Z)
• Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process [56.55075925645864]
  The problem of constrained decision process (CMDP) is investigated, where an agent aims to maximize the expected accumulated discounted reward subject to multiple constraints. A new utilities-dual convex approach is proposed with novel integration of three ingredients: regularized policy, dual regularizer, and Nesterov's gradient descent dual. This is the first demonstration that nonconcave CMDP problems can attain the lower bound of $mathcal O (1/epsilon)$ for all complexity optimization subject to convex constraints.
  arXiv  Detail & Related papers  (2021-10-20T02:57:21Z)
• Optimization on manifolds: A symplectic approach [127.54402681305629]
  We propose a dissipative extension of Dirac's theory of constrained Hamiltonian systems as a general framework for solving optimization problems. Our class of (accelerated) algorithms are not only simple and efficient but also applicable to a broad range of contexts.
  arXiv  Detail & Related papers  (2021-07-23T13:43:34Z)
• Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization [98.0595480384208]
  We propose a generalization extraient spaces which converges to a stationary point. The algorithm applies not only to general $p$-normed spaces, but also to general $p$-dimensional vector spaces.
  arXiv  Detail & Related papers  (2020-10-31T21:35:42Z)

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.