Blind Descent avoids gradient issues, using a different learning approach.
problem Gradient issues like exploding and vanishing gradients.
method Does not use gradients to guide learning; instead, it is a more fundamental learning process.
result Gradient descent is a specific case of Blind Descent.
A new method improves stochastic gradient descent for faster and more efficient estimation.
problem Efficient and fast parametric estimation methods.
method Projected stochastic gradient descent corrected by Fisher scoring.
result The method is faster and more efficient than traditional methods.
Recent years have seen increased interest in performance guarantees of gradient descent algorithms for non-convex optimization. A number of works have uncovered that gradient noise plays a critical role in the ability of gradient descent recursions to efficiently escape saddle-points and reach second-order stationary p…
AGD converges in polynomial iterations to optimal matrix factorization.
problem Matrix factorization optimization with alternating gradient descent.
method Alternating gradient descent with fixed step size, proving convergence in polynomial iterations.
result AGD reaches ε-optimal factorization in T iterations with high probability.
ScaledGD improves gradient descent for ill-conditioned low-rank matrix estimation.
problem Efficiently solving ill-conditioned low-rank matrix estimation problems.
method Scaled Gradient Descent (ScaledGD) with adaptive pre-conditioners.
result Linear convergence rate independent of condition number, low per-iteration cost.
Alt-GDA outperforms Sim-GDA in minimax games with near-optimal local convergence.
problem Minimax optimization convergence rate comparison
method Alternating Gradient Descent-Ascent (Alt-GDA) vs. Simultaneous Gradient Descent-Ascent (Sim-GDA)
result Alt-GDA achieves near-optimal local convergence rate for strongly convex-strongly concave problems, while Sim-GDA converges slower.
This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating bac…
SAGD uses Langevin algorithm for efficient gradient descent.
problem Efficiently approximating gradients in complex models.
method Langevin algorithm for biased but asymptotically accurate gradients.
result Theoretical convergence guarantee for SAGD.
Paper proposes algorithms for solving nonconvex-nonconcave problems with complexity guarantees.
problem Nonconvex-nonconcave minimax problems with PL condition.
method Zeroth-order AGDA and VRAGDA algorithms.
result Iteration complexities for obtaining ε-stationary points.
A new method for SVGD reduces variance in high dimensions.
problem High-dimensional variance in SVGD.
method Grassmann Stein Variational Gradient Descent (GSVGD) projects onto arbitrary subspaces and uses coupled Grassmann-valued diffusion.
result GSVGD explores high-dimensional problems with intrinsic low-dimensional structure efficiently.
New method improves MMD estimation without convexity assumptions.
problem Lack of theoretical guarantees for MMD estimation algorithms.
method Preconditioned gradient descent (PGD) scheme for MMD optimization.
result PGD scheme converges globally under specific conditions.
SoftAD improves classification accuracy with less fine-tuning and fewer computational costs.
problem Improving classification accuracy with less fine-tuning and fewer computational costs.
method SoftAD is a softened, pointwise mechanism that downweights borderline points and limits the effects of outliers.
result SoftAD achieves classification accuracy competitive with flooding and SAM, with a smaller loss generalization gap and model norm.
New method learns good initialization for gradient descent from past solutions.
problem Challenges in solving non-convex optimization problems.
method Learning good initialization rules from previous solutions.
result Our approach performs better than random initialization in various non-convex problems.
APGD algorithm efficiently recovers over-parameterized matrices from noisy measurements.
problem Matrix sensing problem with over-parameterization and noisy measurements.
method Alternating preconditioned gradient descent (APGD) algorithm incorporating preconditioning terms.
result APGD converges to a near-optimal error at a linear rate.
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.
Replication confirms CGD's effectiveness in competitive games.
problem Reproducibility of a novel Nash equilibrium algorithm.
method Replicated experiments and provided Python implementation.
result CGD avoids oscillatory and divergent behaviours.
New method improves online covariance estimation for SGD.
problem Improving online covariance estimation for SGD.
method Proposes a de-biased covariance estimator that eliminates second-order derivatives.
result Achieves a convergence rate of n ( α − 1 ) / 2 log n n^{(α-1)/2} \sqrt{\log n} n ( α − 1 ) /2 log n , outperforming existing methods. The alternating gradient descent (AGD) is a simple but popular algorithm which has been applied to problems in optimization, machine learning, data ming, and signal processing, etc. The algorithm updates two blocks of variables in an alternating manner, in which a gradient step is taken on one block, while keeping the …
This work improves dictionary learning speed without sacrificing accuracy.
problem Prohibitive computational cost of standard dictionary learning methods.
method Approximate dictionary learning using unrolling and gradient descent.
result Unrolling outperforms standard methods in support estimation and early iterations.
Non-negative matrix factorization is a basic tool for decomposing data into the feature and weight matrices under non-negativity constraints, and in practice is often solved in the alternating minimization framework. However, it is unclear whether such algorithms can recover the ground-truth feature matrix when the wei…
TSSM splits neural networks for parallel training with minimal accuracy loss.
problem Accuracy degradation in parallel training of deep neural networks.
method TSSM reformulates alternating minimization to achieve parallelism with minimal accuracy loss.
result TSSM achieves significant speedup without accuracy loss on multiple datasets.
The paper analyzes the variance of different shuffling methods in stochastic gradient descent.
problem Understanding the variance of different shuffling methods in stochastic gradient descent.
method Power spectral density analysis to study the noise sequences of stochastic gradients.
result The stationary variances of iterates decrease in the order of SGD, SGD-RR, and SGD-SO.
New algorithm solves federated minimax optimization problems.
problem Federated minimax optimization challenges.
method Federated Stochastic Smoothed Gradient Descent Ascent (FESS-GDA).
result FESS-GDA uniformly solves federated minimax problems.
Develops DP-SCD for stochastic coordinate descent, making it differentially private.
problem Privacy leak in auxiliary information during stochastic coordinate descent training.
method Develops DP-SCD, leveraging independent noise addition and decoupling/parallelizing coordinate updates.
result Demonstrates competitive performance against DP-SGD with less tuning.
A new ODE model explains gradient descent dynamics near edge of stability.
problem Understanding gradient-based training over non-convex landscapes.
method Rod Flow, a new ODE approximation of GD dynamics.
result Rod Flow accurately predicts critical sharpness threshold and self-stabilization in quartic potentials.
The paper explores how symmetries and noise in SGD influence parameter dynamics.
problem Understanding the dynamics of parameter updates in SGD with symmetries.
method Proved the existence of noise equilibria and showed their role in balancing gradient noise.
result Gradient noise creates a systematic motion of parameters to a unique fixed point, called noise equilibria.
In several experimental reports on nonconvex optimization problems in machine learning, stochastic gradient descent (SGD) was observed to prefer minimizers with flat basins in comparison to more deterministic methods, yet there is very little rigorous understanding of this phenomenon. In fact, the lack of such work has…
Python package for ordinal regression using gradient boosting.
problem Handling ordinal variables in machine learning.
method Gradient boosting with latent variable framework.
result Performs joint optimization of latent function and threshold vector.
Optimizes neural networks' last layer with closed-form solutions.
problem Optimizing neural networks' last layer with stochastic gradient descent.
method Adapting closed-form last layer optimization for stochastic gradient descent, alternating between backbone and last layer updates.
result The method converges to optimal solutions and outperforms standard SGD and Adam in regression tasks.
Max-affine regression method converges linearly using GD and SGD.
problem Regression of max-affine models in signal processing and statistics.
method Gradient descent and mini-batch stochastic gradient descent analysis.
result GD and SGD converge linearly to a neighborhood of the ground truth under sub-Gaussian assumptions.
A new method for robust training under label noise using weighted gradient descent.
problem Overfitting to noisy examples in machine learning.
method Exponentiated gradient reweighting for flexible handling of noisy data.
result Improved generalization in noisy classification and PCA problems.
Adapting functional gradients improves FGD's practicality and theoretical guarantees.
problem Implementing FGD in practice due to infinite-dimensional functional gradients.
method Adapting the representation of functional gradients.
result Establishes convergence to a stationary point for smooth losses and a global minimizer under smoothness + Polyak-Lojasiewicz condition.
Stein variational gradient descent improves inference in Gaussian process models.
problem Inference in Gaussian process models with non-Gaussian likelihoods and large data volumes is computationally intensive and inaccurate with traditional methods.
method Stein variational gradient descent (SVGD) for non-parametric inference.
result SVGD monotonically decreases the Kullback-Leibler divergence from the sampling distribution to the true posterior.
New Muon and Momo variants improve neural network optimization robustness.
problem Improving neural network optimization methods.
method Systematic exploration of non-Euclidean gradient descent variants.
result Momo variants of Muon are more robust to hyperparameter tuning.
A new biased gradient descent method for conditional stochastic optimization.
problem Challenges in constructing unbiased gradient estimators for conditional stochastic optimization.
method Proposes a biased stochastic gradient descent (BSGD) algorithm and analyzes its sample complexities.
result Establishes sample complexities of BSGD for various objectives and shows that BSpiderBoost matches the lower bound complexity.
Momentum based stochastic gradient methods such as heavy ball (HB) and Nesterov's accelerated gradient descent (NAG) method are widely used in practice for training deep networks and other supervised learning models, as they often provide significant improvements over stochastic gradient descent (SGD). Rigorously speak…
We show that accelerated gradient descent, averaged gradient descent and the heavy-ball method for non-strongly-convex problems may be reformulated as constant parameter second-order difference equation algorithms, where stability of the system is equivalent to convergence at rate O(1/n 2), where n is the number of ite…
Ad-SVGD optimizes kernel parameters for SVGD, improving inference performance.
problem Efficiently approximating posterior distributions in Bayesian inference.
method Adaptive kernel selection for SVGD dynamics.
result Ad-SVGD outperforms standard heuristics in various tasks.
A new catnat function improves gradient descent for categorical variables.
problem Gradient descent challenges with discrete latent categorical variables.
method Replaced softmax with catnat, a hierarchical binary split function.
result Catnat function offers significant advantages in gradient descent.
Hybridizes CEM and gradient descent for efficient model-predictive control.
problem Efficiently planning optimal action sequences in high-dimensional spaces.
method Interleaves Cross-Entropy Method (CEM) and gradient descent steps.
result Faster convergence and avoidance of local optima compared to CEM.
A scalable method for heavy-tailed gradients using cheap stochastic sub-processes.
problem Scalability issues with robust gradient descent under heavy-tailed gradients.
method Cheap stochastic sub-processes for a single pass over partitioned data.
result Improved scalability and robustness to perturbations.
Paper proposes a new method to separate low rank and sparse matrices without bias.
problem Recovering low rank and sparse matrices from measurements.
method Uses nonconvex regularizers and alternating proximal gradient descent.
result Error bounds for the algorithm applied to sparse optimization, matrix completion, and robust PCA.
Proposes HTM for aggregating ranked data considering user accuracy.
problem Aggregating ranked data from heterogeneous users with varying accuracy levels.
method Heterogeneous Thurstone Model (HTM) with alternating gradient descent algorithm.
result Algorithm converges linearly and outperforms existing methods.
In this paper, we briefly review the basic scheme of the pseudoinverse learning (PIL) algorithm and present some discussions on the PIL, as well as its variants. The PIL algorithm, first presented in 1995, is a non-gradient descent and non-iterative learning algorithm for multi-layer neural networks and has several adv…
Constructs retractions of CAT(1) spaces to convex subsets.
problem Geometric description of an analytic tool.
method Gradient flow of time-dependent locally Lipschitz semiconcave functions.
result Existence of gradient flows proved for independent interest.
SimpleMKKM improves multi-kernel clustering efficiency.
problem Efficient multi-kernel clustering.
method Re-formulated minimization-maximization problem into a smooth minimization, solved with gradient descent.
result Outperforms state-of-the-art multi-kernel clustering alternatives.
Natural gradient descent is an optimization method traditionally motivated from the perspective of information geometry, and works well for many applications as an alternative to stochastic gradient descent. In this paper we critically analyze this method and its properties, and show how it can be viewed as a type of 2…
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.