cs.LGOct 6, 2025

Closed-Form Last Layer Optimization

Authors: Alexandre Galashov, Nathaël Da Costa, Liyuan Xu, Philipp Hennig, Arthur Gretton

Organizations: Google DeepMind Gatsby Unit, University College London · Tübingen AI Center, University of Tübingen · Secondmind†

Abstract

Neural networks are typically optimized with variants of stochastic gradient descent. Under a squared loss, however, the optimal solution to the linear last layer weights is known in closed-form. We propose to leverage this during optimization, treating the last layer as a function of the backbone parameters, and optimizing solely for these parameters. We show this is equivalent to alternating between gradient descent steps on the backbone and closed-form updates on the last layer. We adapt the method for the setting of stochastic gradient descent, by trading off the loss on the current batch against the accumulated information from previous batches. We provide theoretical analyses showing convergence of the method to an optimal solution in the neural tangent kernel regime, as well as quantifying the gains compared to standard SGD in a one-step analysis. Finally, we demonstrate the effectiveness of our approach compared with SGD and Adam on a squared loss in several regression tasks, including neural operators and causal inference.

Figures & tables

Appendix figures & tables22 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Apr 1, 2026

Sven: Singular Value Descent as a Computationally Efficient Natural Gradient Method

We introduce Sven (Singular Value dEsceNt), a new optimization algorithm for neural networks that exploits the natural decomposition of loss functions into a sum over individual data points, rather than reducing the full loss to a single scalar before computing a parameter update. Sven treats each data point's residual as a separate condition to be satisfied simultaneously, using the Moore-Penrose pseudoinverse of the loss Jacobian to find the minimum-norm parameter update that best satisfies all conditions at once. In practice, this pseudoinverse is approximated via a truncated singular value decomposition, retaining only the kk most significant directions. We show that Sven can be understood as a natural gradient method generalized to the overparametrized regime, recovering natural gradient descent in the underparametrized limit. We test Sven on a variety of regression and classification tasks, including small-scale language modeling with transformers, and find that it is competitive with leading baselines such as Adam, Muon, and K-FAC. We also discuss Sven's memory overhead, which presents a barrier to scaling under a naive implementation, and introduce an optimized implementation that keeps memory usage on par with standard baselines under mild restrictions on model architecture. Beyond standard machine learning benchmarks, we anticipate that Sven will find natural application in scientific computing settings where custom loss functions decompose into several conditions.
Sep 30, 2026

Exact information accounting for SGD methods

As an alternative to the standard geometric analyses, we give an exact, information-theoretic analysis of stochastic gradient descent (SGD) and its variants. We show that a preconditioned SGD step is the posterior-mean update of a Gaussian Bayes model, and that its one-step regret splits into an intrinsic-time cost and a change in comparator information. The split extends to an identity for the objective itself. Convex convergence, strict-saddle-point escape, the link between flatness and generalization, the standard learning-rate schedules, adaptive optimizers, and the noisy, momentum, heavy-tailed, and gradient-free variants of SGD each correspond to a term or a special case of this identity. We measure its terms on synthetic and real training runs. On real networks it attributes the slack of classical convergence bounds to the terms their derivations drop and separates optimizers that reach the same training loss. That separation follows the number and consistency of their steps. Its relation to which of them generalizes better differs between networks. For gradient-free SGD the identity determines how a curvature preconditioner should enter the update. The sharpness-based generalization certificate it yields, with a data-independent isotropic prior, is vacuous at network scale unless the curvature spectrum is nearly flat across all parameters.
Aug 17, 2026

On the Principles Behind Neural Network Optimizers

Reliable optimization is central to neural network (NN) training, yet Adam, the default optimizer for modern LLMs, rests on a fragile foundation. This thesis develops a principled grounding for Adam and motivates new designs. First, we revisit Adam's divergence--convergence debate and show the existence of a problem-dependent phase transition: with properly chosen, batch-size-dependent hyperparameters, Adam converges, whereas under small-β2β_2 regimes it can diverge. Second, we investigate why Adam substantially outperforms SGD on Transformers through Hessian structure. We find that the Hessian evolves toward a near-block-diagonal form along training, accompanied by strong block heterogeneity. We prove that this structure makes Adam's diagonal preconditioner effective. We further show that this special Hessian structure originates from consecutive multiplications of large matrix variables, and we provide a rigorous analysis based on random matrix theory. Finally, these insights motivate Adam-mini, a new optimizer that reduces Adam's memory footprint by 50% while preserving its performance. Our results also have broader implications beyond Adam: they reveal new local structures in matrix-based nonconvex problems, and also help understand and improve recent NN optimizers, such as Muon.