Modified Gauss-Newton Algorithms under Noise
Gauss-Newton methods and their stochastic version have been widely used in machine learning and signal processing. Their nonsmooth counterparts, modified Gauss-Newton or prox-linear algorithms, can lead to contrasting outcomes when compared to gradient descent in large-scale statistical settings. We explore the contrasting performance of these two classes of algorithms in theory on a stylized statistical example, and experimentally on learning problems including structured prediction. In theory, we delineate the regime where the quadratic convergence of the modified Gauss-Newton method is active under statistical noise. In the experiments, we underline the versatility of stochastic (sub)-gradient descent to minimize nonsmooth composite objectives.
Code (0)
등록된 구현이 없습니다.
Tasks
Structured PredictionSimilar Papers 제목 키워드 기반
Modified Newton Integration Algorithm With Noise Tolerance Applied to Robotics
Currently, the Newton-Raphson iterative algorithm has been extensively employed in the fields of basic research and engineering. However, when noise components exist in a system, its performance is largely affected. To r…
Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks
In this thesis, we disentangle the generalized Gauss-Newton and approximate inference for Bayesian deep learning. The generalized Gauss-Newton method is an optimization method that is used in several popular Bayesian dee…
Deep LearningGaussian ProcessesBayes-Newton Methods for Approximate Bayesian Inference with PSD Guarantees
We formulate natural gradient variational inference (VI), expectation propagation (EP), and posterior linearisation (PL) as extensions of Newton's method for optimising the parameters of a Bayesian posterior distribution…
Bayesian InferenceGaussian ProcessesState Space Modelsvalid+1DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum
We study differentially private (DP) training with Muon, a matrix-valued optimizer that updates hidden-layer weights using momentum followed by Newton--Schulz orthogonalization. While DP-SGD is well understood, the inter…
Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise
Diagonal preconditioners are computationally feasible approximate to second-order optimizers, which have shown significant promise in accelerating training of deep learning models. Two predominant approaches are based on…