Local GD proves effective for heterogeneous data in federated learning.
problem Minimizing functions from private, heterogeneous data in federated learning.
method Local gradient descent for smooth, convex functions.
result Communication complexity similar to gradient descent in low accuracy regime.
Simple rules ensure gradient descent adapts to local geometry, converging for convex and nonconvex problems.
problem Minimizing convex and nonconvex functions efficiently.
method Two rules: don't increase stepsize too fast and don't overstep local curvature.
result Method converges for convex and nonconvex problems, even with infinite global smoothness.
Adaptive methods improve gradient descent and proximal gradient for convex optimization.
problem Improving efficiency of gradient descent and proximal gradient methods.
method Adaptive versions of GD and ProxGD using local curvature information.
result Proved convergence with local Lipschitz gradient assumptions.
SGD and stochastic gradient descent converge at optimal rates for certain non-convex functions.
problem Optimal convergence rates for non-convex functions under gradient noise.
method Geometric interpretation of the PL-condition to analyze convergence rates.
result Convergence rates of SGD and stochastic gradient descent match those of strongly convex quadratics.
Gradient descent learns useful features even in the NTK regime.
problem The ability of neural networks to learn useful features.
method Local convergence analysis of gradient descent with regularization.
result Gradient descent can capture ground-truth directions for feature learning even after the loss threshold is reached.
Local Gradient Descent with local steps converges to the centralized model in the interpolation regime.
problem Understanding the implicit bias of Local Gradient Descent in the interpolation regime.
method Analyzing the implicit bias of Local Gradient Descent for classification tasks with linearly separable data.
result The aggregated global model from Local-GD converges exactly to the centralized model in the interpolation regime.
Gradient descent achieves exact linear convergence rate for symmetric matrix completion.
problem Low-rank symmetric matrix completion using gradient descent.
method Local analysis of gradient descent for symmetric matrices without additional assumptions.
result Closed-form expression of exact linear convergence rate matches practice.
We show that gradient descent converges to a local minimizer, almost surely with random initialization. This is proved by applying the Stable Manifold Theorem from dynamical systems theory.
New adaptive step-size method for convex optimization without tuning.
problem Optimizing convex functions efficiently with stochastic gradients.
method Adapted Adaptive Gradient Descent Without Descent to stochastic setting.
result Stochastic gradient descent converges under various assumptions.
Gradient descent fails to train two-layer ReLU networks, leading to poor performance.
problem Gradient descent training of two-layer ReLU networks initialized by He et al. (2015) fails to find optimal solutions.
method Gradient descent on a least-squares loss for training two-layer (Leaky)ReLU networks.
result Gradient descent only finds bad local minima, leading to linear regression for non-linear target functions.
LOSSGRAD automatically adjusts learning rates in neural networks.
problem Finding optimal learning rates in gradient descent.
method LOSSGRAD uses quadratic approximation to find locally optimal step-size.
result LOSSGRAD achieves comparable results to other methods while being insensitive to initial learning rate.
Gradient descent-ascent converges to strict local minmax equilibria with a finite timescale separation.
problem Analyzing the convergence of gradient descent-ascent in non-convex, non-concave games with a finite timescale separation.
method Investigates the role of a finite timescale separation parameter τ on gradient descent-ascent in two-player zero-sum games, providing convergence rates and non-convergence results.
result Gradient descent-ascent converges to strict local minmax equilibria for a finite timescale separation parameter τ*.
MSGD outperforms SGD in overparametrized settings with faster convergence rates.
problem Optimization of non-convex functions with momentum.
method Momentum Stochastic Gradient Descent (MSGD) with rigorous analysis.
result MSGD converges exponentially faster than SGD in overparametrized settings.
Preconditioned non-convex gradient descent improves noisy matrix estimation.
problem Estimating low-rank matrices from noisy measurements.
method Preconditioned non-convex gradient descent for noisy measurements.
result Preconditioned method converges to minimax optimal estimate at a linear rate.
Stochastic gradient descent optimizes Nyström samples for kernel matrix approximation.
problem Optimizing Nyström samples for kernel matrix approximation.
method Stochastic gradient descent applied to multisets of landmark points (Nyström samples) using a surrogate criterion (radial SKD).
result Local minimization of the radial SKD yields improved Nyström approximation accuracy.
Gradient descent converges linearly for overparameterized linear networks.
problem Convergence of gradient descent for overparameterized neural networks.
method Local Polyak-Lojasiewicz and Descent Lemma for overparameterized linear models.
result Gradient descent achieves linear convergence for two-layer linear networks under relaxed assumptions.
Paper proposes FR algorithm to solve minimax optimization locally.
problem Gradient descent fails to find local minimax in minimax optimization.
method Follow-the-Ridge (FR) algorithm, addressing rotational behavior of gradient dynamics.
result FR algorithm provably converges to local minimax.
Analytical method finds deeper optima in two-layer ReLU networks.
problem Training two-layer ReLU networks with analytical methods.
method Analytically finding critical points of the loss function for one layer while keeping the other fixed.
result Significantly smaller training loss values on real datasets compared to gradient descent methods.
Gradient descent can take exponentially long to escape saddle points in 2D.
problem Worst-case inefficiency of gradient descent in non-convex optimization.
method Analysis of gradient descent's performance on 2D functions.
result Gradient descent can take exponentially long to escape saddle points.
Paper proposes a pre-conditioning technique to speed up gradient-descent convergence in distributed linear least-squares problems.
problem Expediting convergence of gradient-descent method for ill-conditioned distributed linear least-squares problems.
method Iterative pre-conditioning technique to improve convergence rate of gradient-descent method.
result Pre-conditioned gradient-descent achieves superlinear convergence for unique solutions and improved linear convergence otherwise.
Paper proposes a pre-conditioning method to speed up gradient descent in multi-agent optimization.
problem Speed up convergence of gradient descent in multi-agent optimization problems.
method Iterative pre-conditioning approach to mitigate the effect of problem conditioning.
result Significant improvement in convergence speed of gradient descent method.
We consider the problem of learning a one-hidden-layer neural network with non-overlapping convolutional layer and ReLU activation, i.e., f ( Z , w , a ) = ∑ j a j σ ( w T Z j ) f(\mathbf{Z}, \mathbf{w}, \mathbf{a}) = \sum_j a_jσ(\mathbf{w}^T\mathbf{Z}_j) f ( Z , w , a ) = ∑ j a j σ ( w T Z j ) , in which both the convolutional weights w \mathbf{w} w and the output weights a \mathbf{a} a are paramete…
Algorithm improves online canonical correlation analysis.
problem Online canonical correlation analysis.
method Stochastic Scaled-Gradient Descent (SSGD) for minimizing expectation over Riemannian manifolds.
result Achieved optimal one-time-scale algorithm with explicit rate of local asymptotic convergence.
Stochastic gradient descent is a simple approach to find the local minima of a cost function whose evaluations are corrupted by noise. In this paper, we develop a procedure extending stochastic gradient descent algorithms to the case where the function is defined on a Riemannian manifold. We prove that, as in the Eucli…
SGD method converges to minima for non-convex functions.
problem Non-convex optimization problems in machine learning.
method Stochastic gradient descent method for non-convex objective functions.
result Estimates on the rate of convergence to minima.
We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for a broad family of loss functions, with proper random weight initialization, both…
KSD Descent uses KSD to sample from a target distribution efficiently.
problem Sampling from complex target distributions efficiently.
method Wasserstein gradient flow of KSD, using L-BFGS optimization.
result KSD Descent can sample from a target distribution using a set of particles.
Accelerates ERM problems with LPI-GD and improved oracle complexity.
problem Empirical Risk Minimization (ERM) problems with strong convexity and smoothness.
method Local Polynomial Interpolation-based Gradient Descent (LPI-GD) and accelerated methods.
result Oracle complexity improved to $ ilde{O}\left(\sqrtσ m^d \log(1/\varepsilon)
ight)$ .
Recent work has argued that stochastic gradient descent can approximate the Bayesian uncertainty in model parameters near local minima. In this work we develop a similar correspondence for minibatch natural gradient descent (NGD). We prove that for sufficiently small learning rates, if the model predictions on the trai…
Heavy-tailed distributions emerge in SGD's parameter evolution.
problem Understanding heavy-tailed distributions in SGD parameter evolution.
method Continuous diffusion approximation of SGD (homogenized SGD) analysis.
result Explicit upper and lower bounds on tail-index of homogenized SGD.
We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which scales linearly in the underlying dimension and the number of training examples. The time complexity of our algorithm to find an approximate local minimum is even faster than that of gradie…
Proposes a continuous flow model to understand and control instability in gradient descent for deep learning.
problem Understanding and controlling the instability of gradient descent in deep learning.
method Introduces the Principal Flow (PF), a continuous time flow that approximates gradient descent dynamics.
result The PF captures divergent and oscillatory behaviors of gradient descent, including escaping local minima and saddle points.
Despite the growing prominence of generative adversarial networks (GANs), optimization in GANs is still a poorly understood topic. In this paper, we analyze the "gradient descent" form of GAN optimization i.e., the natural setting where we simultaneously take small gradient steps in both generator and discriminator par…
We analyze stochastic gradient descent for optimizing non-convex functions. In many cases for non-convex functions the goal is to find a reasonable local minimum, and the main concern is that gradient updates are trapped in saddle points. In this paper we identify strict saddle property for non-convex problem that allo…
Proposes Coherent Gradients to explain and reduce overfitting in neural networks.
problem Why neural networks generalize well despite fitting random data.
method Hypothesis about gradient dynamics and a modification to gradient descent.
result Supports hypothesis with heuristic arguments and perturbative experiments.
We study the implicit bias of gradient descent methods in solving a binary classification problem over a linearly separable dataset. The classifier is described by a nonlinear ReLU model and the objective function adopts the exponential loss function. We first characterize the landscape of the loss function and show th…
A new method compresses large datasets for gradient descent algorithms efficiently.
problem Efficiently compress large-scale datasets for gradient descent algorithms.
method Proposes a novel sequential coreset framework based on gradient descent locality.
result Significantly reduces computational complexity and running time.
Gradient descent converges linearly for neural networks with specific conditions.
problem Optimizing neural networks with fixed width and depth.
method Local Polyak-Lojasiewicz criterion for gradient flow and descent.
result Gradient descent converges to zero-loss solutions under certain conditions.
We develop a more efficient NGD method for structured parameters.
problem Computational challenges in NGD for structured parameter spaces.
method Local-parameter coordinates to simplify Fisher-matrix computations.
result New structured second-order algorithms and learning methods.
ECD algorithm speeds up non-convex optimization, offering quantum and stochastic enhancements.
problem Non-convex optimization challenges in machine learning.
method Energy Conserving Descent (ECD) algorithm, stochastic ECD dynamics (sECD), quantum ECD Hamiltonian (qECD).
result ECD and its quantum version achieve exponential speedup over gradient descent.
SGD converges with positive probability for non-convex deep neural networks under specific conditions.
problem Convergence of SGD for non-convex deep neural networks.
method Established local convergence with positive probability under local Łojasiewicz condition and additional structural assumption.
result SGD converges with positive probability for non-convex deep neural networks under specific conditions.
Study local convergence of GDA for training GANs with kernel-based discriminators.
problem Analyzing the local dynamics of GDA for GANs with kernel-based discriminators.
method Linearization of a non-linear dynamical system, under an isolated points model assumption.
result Showed phase transitions indicating convergence, oscillation, or divergence of GDA.
New algorithm corrects bias in LDP-released data for better analysis.
problem Bias in data released under Local Differential Privacy (LDP).
method Inverse Weierstrass Private Stochastic Gradient Descent (IWP-SGD).
result Converges to true population risk minimizer at O ( 1 / n ) \mathcal{O}(1/n) O ( 1/ n ) rate. SGD converges to global minimum for certain non-convex functions.
problem Theoretical challenges in optimizing non-convex functions in machine learning.
method Perturbed SGD on a broad class of non-convex functions.
result SGD converges to global minimum for certain non-convex functions.
LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.
problem Optimizing large, complex design spaces is infeasible and unnecessary.
method LES uses Bayesian optimization to target solutions reachable by iterative optimizers.
result LES achieves strong sample efficiency compared to existing methods.
NGD models have higher effective dimension than SGD models.
problem Measuring model complexity accurately.
method Comparison of NGD and SGD models using effective dimension measures.
result NGD models have a higher effective dimension than SGD models.
A new algorithm solves sparse optimization problems on measures efficiently.
problem Sparse optimization problems on measures.
method Over-parameterized Stochastic Gradient Descent with Random Features.
result Global convergence with rate O ( log ( K ) / K ) O(\log(K)/\sqrt{K}) O ( log ( K ) / K ) and bounded total variation norms. Study on descent algorithms in spiked matrix-tensor models, revealing performance issues and solutions.
problem Analysis of descent algorithms in spiked matrix-tensor models.
method Quantitative analysis using Kac-Rice formula and PDEs for Langevin dynamics.
result Gradient flow dynamics slow down in regions with spurious local minima, while AMP performs well.