Generalization in Supervised Learning Through Riemannian Contraction
- URL: http://arxiv.org/abs/2201.06656v1
- Date: Mon, 17 Jan 2022 23:08:47 GMT
- Title: Generalization in Supervised Learning Through Riemannian Contraction
- Authors: Leo Kozachkov, Patrick M. Wensing, Jean-Jacques Slotine
- Abstract summary: In a supervised learning setting, we show that if an metric 0 is contracting in someian rate $lambda, it is uniformly uniformly rate with $math.
The results hold for gradient and deterministic loss surfaces, in both continuous and stable $-time.
They can be shown to be optimal in certain linear settings, such as over Descent$ convex or strongly convex loss surfaces.
- Score: 4.3604518673788135
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We prove that Riemannian contraction in a supervised learning setting implies
generalization. Specifically, we show that if an optimizer is contracting in
some Riemannian metric with rate $\lambda > 0$, it is uniformly algorithmically
stable with rate $\mathcal{O}(1/\lambda n)$, where $n$ is the number of
labelled examples in the training set. The results hold for stochastic and
deterministic optimization, in both continuous and discrete-time, for convex
and non-convex loss surfaces. The associated generalization bounds reduce to
well-known results in the particular case of gradient descent over convex or
strongly convex loss surfaces. They can be shown to be optimal in certain
linear settings, such as kernel ridge regression under gradient flow.
Related papers
- Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms [18.425648833592312]
We show that tBMM converges to an $ilon$-stationary point within $O(epsilon-2)$.
Under a mild iteration, the results still hold when the subproblem is solved in iterations in each provided the total optimality gap is bounded.
arXiv Detail & Related papers (2024-05-05T22:53:14Z) - Riemannian stochastic optimization methods avoid strict saddle points [68.80251170757647]
We show that policies under study avoid strict saddle points / submanifolds with probability 1.
This result provides an important sanity check as it shows that, almost always, the limit state of an algorithm can only be a local minimizer.
arXiv Detail & Related papers (2023-11-04T11:12:24Z) - Stochastic Gradient Descent for Gaussian Processes Done Right [86.83678041846971]
We show that when emphdone right -- by which we mean using specific insights from optimisation and kernel communities -- gradient descent is highly effective.
We introduce a emphstochastic dual descent algorithm, explain its design in an intuitive manner and illustrate the design choices.
Our method places Gaussian process regression on par with state-of-the-art graph neural networks for molecular binding affinity prediction.
arXiv Detail & Related papers (2023-10-31T16:15:13Z) - Curvature-Independent Last-Iterate Convergence for Games on Riemannian
Manifolds [77.4346324549323]
We show that a step size agnostic to the curvature of the manifold achieves a curvature-independent and linear last-iterate convergence rate.
To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence has not been considered before.
arXiv Detail & Related papers (2023-06-29T01:20:44Z) - Kernel-based off-policy estimation without overlap: Instance optimality
beyond semiparametric efficiency [53.90687548731265]
We study optimal procedures for estimating a linear functional based on observational data.
For any convex and symmetric function class $mathcalF$, we derive a non-asymptotic local minimax bound on the mean-squared error.
arXiv Detail & Related papers (2023-01-16T02:57:37Z) - Randomized Coordinate Subgradient Method for Nonsmooth Composite
Optimization [11.017632675093628]
Coordinate-type subgradient methods for addressing nonsmooth problems are relatively underexplored due to the set of properties of the Lipschitz-type assumption.
arXiv Detail & Related papers (2022-06-30T02:17:11Z) - Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization [116.89941263390769]
We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $min_mathbfxmax_mathbfyF(mathbfx) + H(mathbfx,mathbfy)$, where one has access to first-order oracles for $F$, $G$ as well as the bilinear coupling function $H$.
We present a emphaccelerated gradient-extragradient (AG-EG) descent-ascent algorithm that combines extragrad
arXiv Detail & Related papers (2022-06-17T06:10:20Z) - Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization
under Infinite Noise Variance [17.199063087458907]
We quantify the convergence rate of the Mirror Descent algorithm with a class of uniformly convex mirror maps.
This algorithm does not require any explicit gradient clipping or normalization.
We complement our results with information-theoretic lower bounds showing that no other algorithm using only first-order oracles can achieve improved rates.
arXiv Detail & Related papers (2022-02-23T17:08:40Z) - High-probability Bounds for Non-Convex Stochastic Optimization with
Heavy Tails [55.561406656549686]
We consider non- Hilbert optimization using first-order algorithms for which the gradient estimates may have tails.
We show that a combination of gradient, momentum, and normalized gradient descent convergence to critical points in high-probability with best-known iteration for smooth losses.
arXiv Detail & Related papers (2021-06-28T00:17:01Z) - Curvature-Dependant Global Convergence Rates for Optimization on
Manifolds of Bounded Geometry [6.85316573653194]
We give curvature-dependant convergence rates for weakly convex functions defined on a manifold of 1-bounded geometry.
We compute these bounds explicitly for some manifold commonly used in the optimization literature.
We present self-contained proofs of fully general bounds on the norm of the differential of the exponential map.
arXiv Detail & Related papers (2020-08-06T08:30:35Z) - Tight Nonparametric Convergence Rates for Stochastic Gradient Descent
under the Noiseless Linear Model [0.0]
We analyze the convergence of single-pass, fixed step-size gradient descent on the least-square risk under this model.
As a special case, we analyze an online algorithm for estimating a real function on the unit interval from the noiseless observation of its value at randomly sampled points.
arXiv Detail & Related papers (2020-06-15T08:25:50Z)
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.