End-to-end encrypted neural network improves privacy and compression in federated learning.
problem Privacy and bandwidth issues in gradient updates transmission in federated learning.
method Proposes an end-to-end encrypted neural network to encode and decode gradient updates.
result Effective privacy protection and data compression with minimal accuracy loss.
Unified approach combining gradient descent and multiplicative updates.
problem Combining gradient descent and multiplicative updates for machine learning.
method Introduces hypentropy and a family of matrix-based updates.
result Derives tight regret bounds for the new family of updates.
Gradient methods converge better for alternating updates in bilinear zero-sum games.
problem Understanding the dynamics of gradient algorithms for bilinear zero-sum games.
method Systematic analysis of popular gradient updates for simultaneous and alternating versions of bilinear zero-sum games.
result Alternating updates converge better than simultaneous ones, with optimal parameter setup and rates.
Reparameterizes mirror descent as gradient descent for efficient sparse learning.
problem Efficiently training small sparse networks with mirror descent.
method Develops a framework to convert mirror descent updates into gradient descent updates on different parameters.
result Mirror descent can be reparameterized as gradient descent on modified parameters, facilitating standard backpropagation.
SGD reduces test error by decorrelating updates.
problem Improving generalization error in machine learning models.
method Derive a formula for generalization gap change due to SGD updates, compare to GD, and show decorrelation effect.
result SGD implicitly regularizes generalization error by decorrelating updates.
New implicit Krasulina's k-PCA update avoids QR-decomposition and improves convergence.
problem Online k-PCA problem with orthonormality constraint.
method Derived an implicit form of Krasulina's update that bypasses orthonormality constraint.
result The new update avoids costly QR-decomposition and yields superior convergence.
Paper improves policy updates in reinforcement learning to speed up learning.
problem Slow learning and unlearning in policy optimization.
method Introduces a novel gradient update and a modified policy update.
result Proves modified policy update converges to global optimality.
WarpGrad efficiently learns preconditioning matrices for gradient descent across task distributions.
problem Learning efficient update rules for rapid new task learning.
method Interleaves warp-layers between task-learner layers to meta-learn preconditioning matrices.
result WarpGrad scales to large meta-learning problems and improves across various learning settings.
Unified framework for analyzing batch updating methods with noisy gradients.
problem Analyzing convergence of batch updating methods with noisy gradients and approximations.
method Unified framework using convergence of stochastic processes.
result Establishes a general theorem for most known convergence results.
This study analyzes adversarial training on linearly separable data and finds that gradient updates can achieve large margins in polynomial iterations.
problem Ensuring robustness in machine learning models trained on linearly separable data.
method Analysis of adversarial training with gradient updates on linearly separable data.
result Gradient updates in adversarial training can achieve large margins in polynomial iterations, whereas non-smooth methods require exponentially many iterations.
EGAB algorithms improve online portfolio selection.
problem Online portfolio selection problem.
method Generalized exponentiated gradient (EG) updates with Alpha-Beta divergence regularization.
result EGAB algorithms enhance portfolio performance, especially with transaction costs.
This work improves SGD convergence by adaptively adjusting batch sizes.
problem High variance in gradient estimates with small batch sizes.
method Adaptive batch size adjustment based on model training loss.
result Adaptive batch size method requires fewer model updates with same computation.
Federated learning improves by unbiased gradient aggregation and controllable meta updating.
problem Gradient biases and inconsistency between target and optimization objectives in federated averaging.
method Unbiased gradient aggregation with keep-trace gradient descent and gradient evaluation strategy, controllable meta updating with small data samples.
result Faster convergence and higher accuracy with different network architectures in various FL settings.
Proposes a method to balance tasks in multitask learning with a single gradient step update.
problem Balancing tasks in multitask learning to avoid imbalance.
method Gradient-based meta-learning to balance tasks at the gradient level, training shared and task-specific layers separately.
result Achieves state-of-the-art performance on various multitask computer vision problems.
Paper analyzes game dynamics with negative momentum for improved stability and convergence.
problem Complexity and instability in game dynamics, especially in adversarial settings.
method Analyzed gradient-based methods with negative momentum on simple games and adversarial problems.
result Alternating gradient updates with negative momentum achieve convergence in difficult adversarial problems.
U-Clip clips gradients to reduce bias without discarding them.
problem Reduces bias in stochastic gradient descent.
method Maintains a buffer of clipped gradients to add to next iteration.
result U-Clip updates are unbiased on average.
Proposes time-smoothed gradients for more stable online forecasting.
problem Stability and efficiency in online forecasting with SGD.
method Introduces time-smoothed gradients within SGD update rules.
result Time-smoothed gradients yield more stable results than existing methods.
We present a unifying framework for adapting the update direction in gradient-based iterative optimization methods. As natural special cases we re-derive classical momentum and Nesterov's accelerated gradient method, lending a new intuitive interpretation to the latter algorithm. We show that a new algorithm, which we …
Gradient descent with delayed updates converges faster with noise, even when delays are significant.
problem Analyzing convergence of gradient descent with delayed gradients and stochastic noise.
method Novel technique using generating functions for convergence analysis.
result Convergence bounds show that stochastic noise mitigates the negative effects of delays, improving performance.
Paper proves multiplicative weight updates can train neural networks without learning rate tuning.
problem Vanishing and exploding gradients in gradient descent for compositional functions.
method Proves descent lemma for compositional functions using multiplicative weight updates and derives Madam optimizer.
result Madam optimizer trains state-of-the-art neural networks without learning rate tuning.
The rise of deep learning in recent years has brought with it increasingly clever optimization methods to deal with complex, non-linear loss functions. These methods are often designed with convex optimization in mind, but have been shown to work well in practice even for the highly non-convex optimization associated w…
A new method for machine learning updates reduces complexity and improves robustness.
problem Stochastic gradient updates are inefficient and sensitive to feature scaling.
method Incremental Gauss-Newton Descent (IGND) reduces the need for matrix operations and improves robustness.
result IGND improves robustness to sensitivity scaling and can be competitive with common stochastic optimizers.
SGP combines PushSum with stochastic gradient updates for robust distributed deep learning.
problem Synchronization issues in distributed deep learning.
method Stochastic Gradient Push (SGP) using PushSum for approximate distributed averaging.
result SGP converges to a stationary point at the same rate as SGD and achieves consensus.
RSO uses random weight perturbations to train deep networks without gradients.
problem Training deep neural networks efficiently and without gradient information.
method RSO is a gradient-free Markov Chain Monte Carlo approach that updates weights based on mini-batch loss reduction.
result RSO achieves high accuracy (99.1% on MNIST) with significantly fewer updates than traditional methods.
The paper deals with learning probability distributions of observed data by artificial neural networks. We suggest a so-called gradient conjugate prior (GCP) update appropriate for neural networks, which is a modification of the classical Bayesian update for conjugate priors. We establish a connection between the gradi…
A new black-box optimizer using implicit natural gradient.
problem Efficient optimization for complex, computationally intensive problems.
method Stochastic update with implicit natural gradient of an exponential-family distribution.
result Theoretical convergence rate for convex functions and continuous non-differentiable functions.
AdaDPIGU improves privacy in deep learning by adaptively clipping and pruning gradients.
problem Privacy in deep learning models, especially in high-dimensional settings.
method Importance-based gradient updates, adaptive clipping, differentially private SGD.
result AdaDPIGU achieves high accuracy while maintaining privacy, outperforming non-private models.
Stochastic gradient descent procedures have gained popularity for parameter estimation from large data sets. However, their statistical properties are not well understood, in theory. And in practice, avoiding numerical instability requires careful tuning of key parameters. Here, we introduce implicit stochastic gradien…
SVAG method examines biased updates in variance-reduced stochastic gradient methods.
problem Examining biased updates in variance-reduced stochastic gradient methods.
method Introduces SVAG, a SAG/SAGA-like method with adjustable bias, analyzed in a cocoercive root-finding setting.
result SVAG's step-size requirements for gradients are less restrictive compared to non-gradient cases, highlighting the need for careful analysis.
FedBuff improves federated learning scalability with asynchronous updates.
problem Limited scalability of federated learning with synchronous updates.
method Introduces asynchronous updates (staleness) in federated learning.
result Theoretical analysis shows improved convergence rate with boundedness removed.
Unified perspective on natural gradient methods for GMMs, improving variational inference.
problem Efficiently learning multi-modal approximations of complex distributions.
method Comparison and optimization of VIPS and iBayes-GMM methods for Gaussian mixture models.
result Hybrid approach significantly outperforms both VIPS and iBayes-GMM.
A new principle for optimizer selection improves training speed and performance.
problem Finding the best optimizer hyperparameters for faster training.
method Formulate optimizer selection as maximizing the expected drop rate in loss, treating gradients and updates as signals and an optimizer as a causal filter.
result Greedy optimizer selection yields stable and effective momentum rules.
Bio-inspired neural networks use predictive coding for efficient weight updates.
problem Training artificial neural networks efficiently and biologically plausibly.
method Predictive Coding (PC) updates weights locally using only local information.
result PC provides theoretical advantages like automatic gradient scaling.
PES method reduces bias in gradient estimation for unrolled graphs.
problem High variance and bias in gradient estimation for unrolled computation graphs.
method Divide graph into unrolls, apply ES update, accumulate correction terms.
result PES provides unbiased, low-variance gradient estimates.
Asynchronous distributed stochastic gradient descent methods have trouble converging because of stale gradients. A gradient update sent to a parameter server by a client is stale if the parameters used to calculate that gradient have since been updated on the server. Approaches have been proposed to circumvent this pro…
Muon replaces matrix gradient with polar factor, optimizing flat spectrum updates
problem Optimization bias in matrix updates
method Using polar factor of gradient
result Muon update maximizes entropy among bounded updates
ROIPCA and fROIPCA are online PCA algorithms using rank-one updates.
problem Memory-restricted online PCA for large or streaming data.
method ROIPCA and fROIPCA use rank-one updates for efficient computation.
result fROIPCA is faster with comparable accuracy; ROIPCA is more accurate.
Paper proves SHB convergence with biased gradients and approximate step sizes.
problem Establishing convergence of SHB with biased gradients and approximate step sizes.
method Generalizes SHB convergence conditions for biased gradients, approximate step sizes, and block updating.
result Proves convergence of SHB with new conditions for biased gradients and approximate step sizes.
Gradient-EM Bayesian meta-learning accelerates adaptation with reduced computation and improved robustness.
problem Efficient and robust adaptation to new tasks with uncertainty assessment.
method Extends Bayesian meta-learning with gradient-EM algorithm, decoupling inner-update from meta-update.
result Improves accuracy with less computation cost and enhanced robustness to uncertainty.
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.
QBVI uses natural gradients for efficient Bayesian learning.
problem Efficient Bayesian learning in complex models.
method Natural gradient updates in a black-box framework for exponential-family distributions.
result QBVI framework is effective for a wide range of Bayesian inference problems.
Zeno++ improves robustness of asynchronous SGD in fully asynchronous settings.
problem Byzantine failures in fully asynchronous SGD.
method Estimates descent of loss after applying candidate gradient.
result Proves convergence for non-convex problems under Byzantine failures.
Proposes VSGD optimizer combining probabilistic and gradient-based methods.
problem Uncertainty modeling in deep neural networks.
method Combines probabilistic and gradient-based approaches using SVI.
result VSGD outperforms Adam and SGD on image classification tasks.
GFM models neural network training as a dynamical system to forecast final weights.
problem Computational intensity and inefficiency in training deep neural networks.
method Gradient Flow Matching (GFM) treats training as a dynamical system with learned vector fields.
result GFM achieves forecasting accuracy competitive with Transformer-based models and significantly outperforms classical baselines.
Humans are able to accelerate their learning by selecting training materials that are the most informative and at the appropriate level of difficulty. We propose a framework for distributing deep learning in which one set of workers search for the most informative examples in parallel while a single worker updates the …
We develop methods for parameter estimation in settings with large-scale data sets, where traditional methods are no longer tenable. Our methods rely on stochastic approximations, which are computationally efficient as they maintain one iterate as a parameter estimate, and successively update that iterate based on a si…
Paper proposes recycling model updates in federated learning by exploiting low-rank gradient subspaces.
problem Large parameter transmissions in federated learning.
method Look-back Gradient Multiplier (LBGM) algorithm exploiting low-rank property of gradient subspaces.
result LBGM reduces communication overhead with minimal performance loss.
Paper introduces a new gradient statistic to improve deep learning convergence.
problem Fluctuation effect of gradient updates between iterations.
method Introduces an unbiased stratified statistic \(\bar{G}_{mst}\) and a new algorithm MSSG.
result MSSG algorithm outperforms other sgd-like algorithms in training deep models.