Quantized Adam reduces communication cost in deep learning training.
problem Reducing communication cost in distributed deep learning training.
method Gradient and weight quantization with error feedback in Adam.
result Proposed methods converge to first-order stationary points.
New techniques improve distributed training with compressed gradients.
problem Gradient mismatch problem in local error feedback.
method Step-ahead error feedback and error averaging techniques.
result Our methods handle gradient mismatch and train faster than full-precision training.
Sign-based algorithms (e.g. signSGD) have been proposed as a biased gradient compression technique to alleviate the communication bottleneck in training large neural networks across multiple workers. We show simple convex counter-examples where signSGD does not converge to the optimum. Further, even when it does conver…
This paper analyzes error feedback in compressed federated learning for non-convex optimization problems.
problem Reducing communication cost in federated learning with biased gradient compression.
method Proposes Fed-EF, a compressed federated learning scheme with error feedback, and analyzes its convergence rate and performance under partial client participation.
result Fed-EF can match the convergence rate of full-precision FL under data heterogeneity with a linear speedup and no extra slow-down factor due to stale error compensation.
EF21-Muon optimizes deep learning with error feedback, improving efficiency and accuracy.
problem Lack of principled distributed frameworks for non-Euclidean LMO-based optimizers.
method Introduces EF21-Muon, a communication-efficient, non-Euclidean LMO-based optimizer with convergence guarantees.
result First efficient distributed implementation of non-Euclidean LMO-based optimizers, achieving up to 7x communication savings.
SA-PEF improves federated learning efficiency by correcting gradient mismatches.
problem Slow decay of residual error in federated learning under non-IID data.
method Integrates step-ahead correction with partial error feedback.
result Achieves faster convergence and target accuracy compared to standard EF.
Efficient distributed learning with Byzantine-resilient thresholding and error feedback.
problem Byzantine-resilient distributed learning with communication efficiency.
method Simple thresholding for Byzantine mitigation, compressed gradients and norms for aggregation, error feedback.
result Statistical error rate matches Yin et al.~\cite{dong} but with simpler schemes, and improved convergence with error feedback.
New method tackles composite optimization with error feedback.
problem Challenges in distributed machine learning training and message compression.
method Combines Dual Averaging with EControl for composite optimization.
result First strong convergence analysis for composite optimization with error feedback.
ESM-CNN uses error feedback to build a random CNN for time series forecasting.
problem Improving time series forecasting accuracy with CNNs.
method Incrementally adding random filters and neurons to adaptively construct a CNN.
result ESM-CNN outperforms state-of-the-art models in prediction accuracy and efficiency.
Clip21 improves convergence of gradient-clipped methods in DP settings.
problem Gradient clipping introduces bias in distributed training, causing convergence issues.
method Clip21 designs an error feedback mechanism to mitigate bias in gradient-clipped methods.
result Clip21 converges at the same rate as distributed gradient descent, improving from previous $\mathcal{O}\left(\frac{1}{\sqrt{K}}
ight)$ to $\mathcal{O}\left(\frac{1}{K}
ight)$ .
Improved error feedback method reduces communication complexity in distributed training.
problem Improving convergence in distributed training methods with compression techniques.
method Introduced and improved a modern form of error feedback (EF21) by reducing its theoretical communication complexity.
result Communication complexity depends on the arithmetic mean of smoothness parameters, leading to significant improvements.
New method improves optimization and DP in FL.
problem Combining strong DP and optimization in FL.
method Combining clipping, momentum, and error feedback.
result Optimal convergence rate and near optimal DP guarantees.
Safe-EF improves federated learning for non-smooth, constrained optimization.
problem Federated learning's communication bottlenecks with high-dimensional model updates.
method Error feedback (EF) for non-smooth convex optimization with safety constraints.
result Safe-EF matches lower complexity bounds and ensures safety constraints.
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.
Muon fails to converge on convex Lipschitz functions.
problem Understanding the convergence of Muon on convex and Lipschitz functions.
method Analyzing Muon's performance on convex and Lipschitz functions without error feedback.
result Muon does not converge on convex and Lipschitz functions, regardless of learning rate schedule.
A new method improves communication efficiency in distributed learning.
problem Reducing communication overhead in distributed machine learning.
method Transforming contractive compressors into induced unbiased compressors.
result Significant improvements in memory requirements and communication complexity.
Gradient descent with error feedback performs better than vanilla when features are rare.
problem Improving communication complexity in distributed optimization with rare features.
method Gradient descent with greedy sparsification and error feedback for rare features.
result Communication complexity improves as features become more rare, potentially better than vanilla GD.
Paper introduces MoTEF for faster decentralized optimization with compressed communication.
problem Efficiency bottleneck in decentralized machine learning applications.
method Integrates communication compression with Momentum Tracking and Error Feedback.
result Significantly outperforms existing methods under arbitrary data heterogeneity.
EF21 improves convergence in distributed machine learning models.
problem Improving convergence in distributed machine learning models.
method Proposes EF21, a new error feedback mechanism.
result EF21 achieves a fast O ( 1 / T ) O(1/T) O ( 1/ T ) convergence rate for smooth nonconvex problems. New algorithm for differentially private distributed optimization of smooth, non-convex problems.
problem No differentially private distributed method for smooth, non-convex optimization problems.
method Smoothed normalization integrated with an error-feedback mechanism.
result Achieves superior convergence rate and first differentially private distributed optimization algorithm with provable convergence guarantees.
Enhanced TSFMs improve time series forecasting accuracy and reliability.
problem Variance, bias, and uncertainty in TSFMs' predictions on real data.
method Statistical and ensemble techniques including bagging, stacking, residual modeling, and prediction intervals.
result Hybrid models consistently outperform standalone TSFMs across multiple horizons.
Boolean logic used for neural network training and inference, with convergence analysis.
problem Discrete optimization in neural networks with Boolean logic.
method Boolean logic backpropagation with convergence analysis.
result First convergence analysis for Boolean logic in neural networks.
Paper analyzes and compares ELF algorithms for federated learning.
problem Improving efficiency and privacy in federated learning.
method Proposes P-ELF, D-ELF, and B-ELF algorithms with primal, dual, and bidirectional compression.
result Provides non-asymptotic convergence guarantees under Log-Sobolev inequality.
COMP-AMS optimizes distributed training with compressed gradients, achieving similar accuracy with less communication.
problem Efficiently training large-scale models in distributed environments with reduced communication costs.
method Distributed optimization framework using gradient averaging and adaptive AMSGrad, with gradient compression and error feedback.
result COMP-AMS achieves the same convergence rate and linear speedup as standard AMSGrad with less communication.
LDAdam optimizes large models with low memory by adapting to lower-dimensional subspaces.
problem Training large models efficiently and accurately.
method Adaptive optimization in lower-dimensional subspaces with a new projection-aware update rule and error feedback mechanism.
result LDAdam achieves accurate and efficient training of language models.
New methods improve distributed optimization on non-iid data.
problem Communication bottleneck in distributed machine learning models.
method Two types of distributed gradient compression methods (D-QSGD and D-EF-SGD) analyzed for non-iid data.
result D-EF-SGD performs better than D-QSGD on non-iid data but can still slow down with high data skewness.
Proposes Stochastic-Sign SGD for federated learning with theoretical guarantees.
problem Developing efficient, private, and resilient parameter estimation methods for federated learning.
method Introduces Stochastic-Sign SGD, a novel method based on SIGNSGD, which addresses convergence and communication efficiency.
result Demonstrates the effectiveness of Stochastic-Sign SGD through experiments on MNIST and CIFAR-10 datasets.
New method reduces communication costs in distributed nonconvex optimization.
problem Large communication costs between central server and local workers in distributed learning.
method Communication-compressed AMSGrad for distributed nonconvex optimization.
result Converges to first-order stationary point with same iteration complexity as vanilla AMSGrad.
FP uses random projections to train networks without feedback, achieving comparable performance to backpropagation.
problem Training neural networks without feedback from downstream layers.
method Forward Projection (FP) method that uses randomised nonlinear projections and closed-form regression.
result FP achieves comparable generalisation to backpropagation methods with a single forward pass, offering significant speedup.
Communication overhead is a major bottleneck hampering the scalability of distributed machine learning systems. Recently, there has been a surge of interest in using gradient compression to improve the communication efficiency of distributed neural network training. Using 1-bit quantization, signSGD with majority vote …
FedSGM tackles constrained federated learning with unified framework.
problem Functional constraints, communication bottlenecks, local updates, and partial client participation in federated learning.
method Unified framework based on switching gradient method, incorporating bi-directional error feedback, and soft switching for stability.
result Achieves O ( 1 / T ) \boldsymbol{\mathcal{O}}(1/\sqrt{T}) O ( 1/ T ) convergence rate with high-probability bounds decoupling from sampling noise. We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-convex and non-convex functions and derive concise, non-asymptotic, convergence rates. We show that the rate of convergence in all cases consists of two terms: (i) a stochastic term which is not affected by the delay, and (ii) a higher …
We show LLMs can be locally linear, enabling better control of activations.
problem Suboptimal control of LLM activations during generation.
method Model LLM inference as a linear dynamical system, compute feedback controllers using Jacobians, and adapt classical control theory.
result Robust, fine-grained control of LLM activations across models and tasks.
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.
Unified sign-based compression for federated learning with faster convergence.
problem High communication cost in federated learning with large-scale models.
method Unified noisy perturbation scheme for sign-based compression.
result Achieves faster convergence rate than existing sign-based methods.
New biased compression methods lead to faster convergence in distributed learning.
problem Improving convergence rates in distributed learning with biased compression.
method Study of three classes of biased compression operators in distributed learning.
result Biased compressors can lead to linear convergence rates in both single node and distributed settings.
Gradient flossing stabilizes RNN training by controlling Lyapunov exponents.
problem Gradient instability in RNNs leading to exploding and vanishing gradients.
method Regularizing Lyapunov exponents through backpropagation using differentiable linear algebra.
result Gradient flossing improves RNN training success rate and convergence speed.
A major challenge in cognitive science and AI has been to understand how autonomous agents might acquire and predict behavioral and mental states of other agents in the course of complex social interactions. How does such an agent model the goals, beliefs, and actions of other agents it interacts with? What are the com…