Minibatch SGD outperforms Local SGD in heterogeneous distributed learning.
problem Optimizing a combined convex objective with stochastic gradient estimates from different machines.
method Analysis of Minibatch SGD and Local SGD in a heterogeneous distributed setting.
result Minibatch SGD dominates Local SGD in the heterogeneous distributed setting.
Study reveals convergence properties of SGD with random learning rate.
problem Analyzing convergence of SGD with random learning rate in non-convex optimization.
method Introduced Poisson SGD with random learning rate and used stationary distribution analysis.
result Poisson SGD converges to a stationary distribution and finds global minima in non-convex optimization.
Quantized Epoch-SGD reduces communication in distributed learning.
problem High communication cost in SGD-based distributed learning.
method Quantizes parameters with variance reduction for efficient distributed learning.
result QESGD achieves better performance with less communication compared to other methods.
Local SGD outperforms minibatch SGD for quadratic objectives.
problem Theoretical foundations of local SGD are lacking.
method Proved local SGD strictly dominates minibatch SGD for quadratic objectives and accelerated local SGD is minimax optimal.
result Local SGD does not dominate minibatch SGD in general convex objectives.
Paper shows local SGD outperforms mini-batch SGD under certain conditions.
problem Proving local SGD's superiority in distributed learning with heterogeneous data.
method New lower and upper bounds for local SGD under first-order heterogeneity assumptions.
result Local SGD is min-max optimal under certain conditions, resolving understanding of distributed optimization.
Overlap-Local-SGD improves distributed SGD by overlapping communication and computation.
problem High communication delay and node slowdown in distributed SGD.
method Adding an anchor model to synchronize local updates and pull them towards the anchor model.
result Overlap-Local-SGD speeds up distributed training and mitigates straggler effects.
New algorithm improves distributed SGD with random sparsification for better convergence and generalization.
problem Communication bottleneck in distributed deep learning.
method Proposes detached error feedback (DEF) algorithm to improve convergence and generalization of communication-efficient distributed SGD.
result Shows better convergence and generalization bounds than existing methods.
Qsparse-local-SGD reduces communication in large-scale learning models.
problem Communication bottleneck in distributed optimization of large-scale models.
method Combines sparsification, quantization, and local computation with error compensation.
result Converges at the same rate as vanilla distributed SGD for many sparsifiers and quantizers.
Sketched SGD reduces communication in distributed SGD by sketching gradients.
problem Limited communication in large-scale distributed training of neural networks.
method Introducing Sketched SGD, an algorithm that communicates sketches of gradients instead of full gradients.
result Sketched SGD reduces communication from O(d) or O(W) to O(logd), achieving up to 40x reduction in total communication cost. Paper introduces elastic consistency for distributed SGD, enabling convergence analysis.
problem Training large-scale machine learning models in distributed environments.
method Introduces elastic consistency as a general consistency model for distributed SGD.
result Derives convergence bounds for various distributed SGD methods.
Sparsification improves convergence in asynchronous distributed SGD, even in the presence of staleness.
problem Staleness in asynchronous distributed SGD.
method Applied sparsification to reduce communication overheads in distributed asynchronous settings.
result The ergodic convergence rate of sparsified asynchronous SGD matches that of vanilla SGD, $\mathcal{O} \left( 1/\sqrt{T}
ight)$, even in the presence of staleness.
New bounds for M-SGD show its error distribution is nearly Gaussian.
problem Understanding the error distribution of M-SGD.
method Proved non-asymptotic bounds for M-SGD in Wasserstein distance.
result Error distribution of M-SGD is approximately Gaussian.
UD-SGD analysis shows efficient sampling by a few agents can outperform others.
problem Analyzing convergence speed and sampling strategies in UD-SGD.
method Asymptotic analysis of UD-SGD with various communication patterns and sampling strategies.
result Efficient sampling by a few agents can lead to better overall convergence.
LAGS-SGD optimizes deep learning training by sparsifying gradients layer-wise.
problem Reduces long training times in large deep neural networks with distributed S-SGD.
method Layer-wise adaptive gradient sparsification combined with S-SGD.
result LAGS-SGD achieves convergence guarantees and outperforms vanilla S-SGD.
HybridSGD improves SGD performance by balancing computation and communication.
problem Limited scalability and performance of SGD due to communication costs.
method 2D parallel SGD method (HybridSGD) that trades off between 1D s-step SGD and 1D Federated SGD (FedAvg). result HybridSGD achieves better convergence than FedAvg at similar processor scales and up to 121x speedup over FedAvg.
A new algorithm speeds up deep learning training by decoupling computation and communication.
problem High communication cost limits the speedup of distributed SGD.
method CoCoD-SGD: runs computation and communication in parallel.
result Linear time speedup with respect to hardware resources.
Elastic Gossip distributes neural network training using gossip-like protocols.
problem Distributing neural network training across heterogeneous environments.
method Pairwise-communication using Gossip-like protocols, building on Elastic Averaging SGD.
result Elastic Gossip performs better than Gossiping SGD in experiments, but hyper-parameter search may yield better configurations.
CSER improves SGD efficiency by resetting errors and partial synchronization.
problem Limited scalability of Distributed Stochastic Gradient Descent (SGD) due to communication bottlenecks.
method Introduces 'error reset' technique and partial synchronization for gradients and models.
result Proves convergence for smooth non-convex problems and accelerates distributed training significantly.
Adaptive distributed SGD reduces delay in slow workers.
problem Minimizing delay in distributed SGD with stragglers.
method Adaptive policy for varying k to optimize error-runtime trade-off. result Numerical simulations confirm the effectiveness of the adaptive approach.
STL-SGD accelerates Local SGD by gradually increasing communication periods.
problem Reducing communication complexity in distributed SGD.
method Gradually increasing communication periods while decreasing learning rate.
result Significant reduction in communication complexity with improved convergence rates.
Stochastic gradient descent (SGD) is a popular stochastic optimization method in machine learning. Traditional parallel SGD algorithms, e.g., SimuParallel SGD, often require all nodes to have the same performance or to consume equal quantities of data. However, these requirements are difficult to satisfy when the paral…
SGD-trained neural networks generalize well even with adversarial label noise.
problem Generalization of neural networks trained on adversarial label noise.
method Training a one-hidden-layer neural network with SGD on arbitrary width networks.
result SGD-trained networks achieve classification accuracy competitive with the best halfspace over adversarial label noise.
VRL-SGD reduces communication complexity in non-identical data settings.
problem Training machine learning models with non-identical data distribution.
method VRL-SGD, which eliminates gradient variance dependency and achieves linear speedup with lower communication complexity.
result VRL-SGD reduces communication complexity from $O(T^{ rac{3}{4}} N^{ rac{3}{4}})$ to $O(T^{ rac{1}{2}} N^{ rac{3}{2}})$.
Gradient clipping helps private SGD converge despite potential bias.
problem Gradient clipping in private SGD can bias convergence.
method Theoretical analysis and empirical evaluation of gradient clipping effects.
result Gradient clipping can prevent convergence to stationary points and introduces bias.
Non-convex SGD learns halfspaces with adversarial label noise efficiently.
problem Agnostically learning halfspaces in adversarial label noise settings.
method Non-convex SGD optimization for halfspace learning.
result Non-convex SGD achieves misclassification error close to optimal with adversarial noise.
Top-k sparsification reduces deep learning communication costs.
problem Reducing communication overhead in distributed deep learning.
method Extensive experiments and theoretical analysis of Top-k sparsification.
result A tighter bound for Top-k operator derived, improving scaling efficiency.
LSGD improves deep learning training efficiency by synchronizing and decentralizing SGD.
problem Asynchronous SGD's accuracy issues and synchronous SGD's communication inefficiency.
method LSGD divides nodes into subgroups with centralized communication and decentralized computation.
result LSGD achieves better accuracy and efficiency than synchronous and asynchronous SGD.
Asynchronous SGD generalizes well with enough data, improving stability and reducing error.
problem Generalization performance of asynchronous distributed SGD systems.
method Algorithm stability framework, adaptive learning rate strategy.
result Distributed asynchronous SGD generalizes well with enough data samples.
New algorithm resists up to half of Byzantine workers in distributed learning.
problem Resilience of distributed SGD in the presence of Byzantine attackers.
method Lipschitz-inspired coordinate-wise median approach (LICM-SGD).
result LICM-SGD can resist up to half of Byzantine workers in non-convex settings.
MindFlayer SGD improves parallel SGD for heterogeneous, random compute times.
problem Minimizing nonconvex functions with heterogeneous, random compute times.
method MindFlayer SGD, designed for stochastic and heterogeneous delays.
result MindFlayer SGD outperforms existing methods in environments with heavy-tailed noise.
New algorithm reduces communication in distributed SGD, improving efficiency.
problem Slow communication rounds bottleneck synchronous mini-batch SGD convergence.
method Proposes non-asymptotic error analysis for Local-SGD, comparing to averaging methods.
result Local-SGD reduces communication by a factor of O(√T/P^(3/2)) for large step sizes.
Local SGD proves efficient in overparameterized linear regression.
problem Efficiently learning overparameterized linear models in distributed settings.
method Distributed SGD (DSGD) with overparameterized models.
result Excess risk of SGD is smaller than ridge regression in the same sample complexity.
A2SGD reduces distributed SGD communication to O(1) per worker.
problem Heavy communication costs in distributed SGD for large models.
method Two-level gradient averaging to consolidate gradients to two local averages.
result Achieves O(1) communication complexity per worker, significantly reducing traffic and training time.
Stochastic Gradient Descent (SGD) is an important algorithm in machine learning. With constant learning rates, it is a stochastic process that, after an initial phase of convergence, generates samples from a stationary distribution. We show that SGD with constant rates can be effectively used as an approximate posterio…
Noise balance theory explains SGD's behavior in neural networks.
problem Understanding SGD's navigation in neural network loss landscapes.
method Analyzes minibatch noise and loss function symmetries.
result Derives the stationary distribution of SGD for deep networks.
Ringmaster ASGD improves Asynchronous SGD's efficiency under varying worker times.
problem Suboptimal performance of Asynchronous SGD under heterogeneous worker computation times.
method Ringmaster ASGD, a novel Asynchronous SGD method with optimal time complexity.
result Ringmaster ASGD achieves optimal time complexity under arbitrary worker heterogeneity.
Unified analysis of asynchronous-SGD algorithms for distributed learning.
problem Analyzing asynchronous-SGD in heterogeneous settings with varying speeds and data distributions.
method Unified convergence theory for non-convex smooth functions, including pure asynchronous SGD and its modifications.
result Unified convergence rates for various asynchronous algorithms, including novel methods.
Local SGD outperforms conventional methods in LLM training.
problem Training large language models on distributed devices.
method Local SGD algorithm applied to distributed training.
result Local SGD achieves competitive results in LLM training.
A distributed SGD method for heterogeneous networks with hubs and workers.
problem Learning in heterogeneous multi-level networks with worker heterogeneity and varying communication.
method Multi-Level Local SGD: distributed SGD with hub-and-spoke paradigm and hub averaging.
result The method converges with error dependent on worker heterogeneity, hub network topology, and iterations.
Researchers analyze SGD dynamics using von Mises-Fisher distributions.
problem Understanding the dynamics of stochastic gradient descent in high-dimensional spaces.
method Geometric analysis of minibatch gradient norms and directions through von Mises-Fisher distribution.
result Directional uniformity of minibatch gradients increases over SGD iterations.
The paper examines how SGD noise deviates from Gaussian distribution.
problem Understanding why SGD outperforms GD in neural networks.
method Analysis of SGN vectors' distribution during training.
result For large batch sizes, SGN vectors are mostly Gaussian in early phases.
Improves distributed SGD convergence speed with reduced computation load.
problem Mitigating stragglers in distributed SGD to speed up convergence.
method Modeling communication and computation times, adapting number of workers and computation load dynamically.
result Significantly reduces computation load while improving convergence speed.
Communication-efficient SGD algorithms, which allow nodes to perform local updates and periodically synchronize local models, are highly effective in improving the speed and scalability of distributed SGD. However, a rigorous convergence analysis and comparative study of different communication-reduction strategies rem…
SGD converges to an invariant distribution with sub-Gaussian or sub-exponential properties.
problem Optimizing smooth and strongly convex objectives using SGD.
method Analysis through Markov chains, focusing on convergence and concentration properties.
result SGD iterates and their invariant limit distribution inherit sub-Gaussian or sub-exponential concentration properties.
Asynchronous SGD can speed up training with a trade-off of gradient staleness.
problem Asynchronous SGD suffers from gradient staleness, affecting convergence error.
method Theoretical analysis of the error-runtime trade-off considering random straggling delays.
result A method of gradually varying synchronicity in distributed SGD is proposed and demonstrated.
Paper improves compressed SGD to reach second-order stationary points.
problem Efficiently reaching second-order stationary points in distributed machine learning.
method Gradient compression and RandomK compressor to improve convergence to second-order stationary points.
result Compressed SGD reaches second-order stationary points with improved communication efficiency.
SGD improves DR by solving two-stage sampling problems.
problem Improving the learning properties of SGD for distribution regression.
method Applying SGD to two-stage sampling problems in distribution regression.
result Theoretical guarantees for SGD's performance in DR, with optimal bounds.
A new method reduces communication in distributed learning by 32x.
problem High communication costs in distributed machine learning.
method Distributed compressed SGD with Nesterov's momentum and blockwise compression.
result Achieves 32x reduction in communication cost and converges as fast as full-precision SGD.