Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation. To alleviate this problem, several scalar quantization techniques have been developed to compress the gradients. But these techniques could perform …
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “gradient aggregation”
Paper studies fundamental limits of communication in distributed learning.
problem Communication efficiency in model aggregation for distributed learning.
method Rate-Distortion approach to model aggregation as a vector Gaussian CEO problem.
result Derives rate region bound and sum-rate-distortion function for model aggregation.
The present paper develops a novel aggregated gradient approach for distributed machine learning that adaptively compresses the gradient communication. The key idea is to first quantize the computed gradients, and then skip less informative quantized gradient communications by reusing outdated gradients. Quantizing and…
Non-affine aggregation rules cannot preserve monotonicity in convex learning.
problem Designing non-affine aggregation rules that maintain monotonicity in convex learning.
method Proving that monotonicity of aggregated gradients is preserved only if the aggregation rule is positively affine.
result Non-affine aggregation prevents steady convergence and substantially degrades algorithmic stability.
The incremental aggregated gradient algorithm is popular in network optimization and machine learning research. However, the current convergence results require the objective function to be strongly convex. And the existing convergence rates are also limited to linear convergence. Due to the mathematical techniques, th…
Policy gradient methods with aggregated states can achieve better performance than approximate policy iteration.
problem Approximation errors in policy and value function approximations.
method State-aggregated representations and policy gradient methods.
result Policy gradient methods can achieve a per-period regret bounded by ε, while approximate policy iteration and value iteration have a higher regret.
LASG: Lazily Aggregated Stochastic Gradients for Communication-Efficient Distributed Learningmath.OC
LASG improves communication efficiency in distributed learning.
problem Efficiently communicating gradients in distributed machine learning.
method Develops a new stochastic gradient descent approach, LASG, that predicts and selects significant communication rounds.
result Achieves communication savings by an order of magnitude in federated learning.
Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descen…
This paper presents a new class of gradient methods for distributed machine learning that adaptively skip the gradient calculations to learn with reduced communication and computation. Simple rules are designed to detect slowly-varying gradients and, therefore, trigger the reuse of outdated gradients. The resultant gra…
Robustification of deep net classifiers by key based diversified aggregation with pre-filteringcs.LG
In this paper, we address a problem of machine learning system vulnerability to adversarial attacks. We propose and investigate a Key based Diversified Aggregation (KDA) mechanism as a defense strategy. The KDA assumes that the attacker (i) knows the architecture of classifier and the used defense strategy, (ii) has an…
We propose a novel robust aggregation rule for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilience…
Federated Learning speeds up speech recognition training by 7x and reduces error rate by 6%.
problem Training acoustic models for speech recognition tasks in a federated manner.
method Hierarchical optimization and dynamic gradient aggregation methods.
result Significant improvement in training convergence speed and model performance.
We propose a new algorithm for finite sum optimization which we call the curvature-aided incremental aggregated gradient (CIAG) method. Motivated by the problem of training a classifier for a d-dimensional problem, where the number of training data is and , the CIAG method seeks to accelerate increme…
The paper compares aggregated data labels in curated and random bags for machine learning models.
problem Protecting user privacy in machine learning systems with aggregated data.
method Examined curated and random bags for training machine learning models and compared their performance.
result Gradient-based learning can be performed on aggregated data without performance degradation.
We analyze a fast incremental aggregated gradient method for optimizing nonconvex problems of the form . Specifically, we analyze the SAGA algorithm within an Incremental First-order Oracle framework, and show that it converges to a stationary point provably faster than both gradient descent and s…
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.
PTOPOFL uses topological descriptors to protect privacy in federated learning.
problem Privacy and data reconstruction attacks in federated learning.
method PTOPOFL replaces gradient communication with persistent homology feature vectors for privacy and topology-guided aggregation.
result PTOPOFL achieves higher AUC and reduces reconstruction risk compared to gradient sharing.
Federated learning (FL) aims to train machine learning models in the decentralized system consisting of an enormous amount of smart edge devices. Federated averaging (FedAvg), the fundamental algorithm in FL settings, proposes on-device training and model aggregation to avoid the potential heavy communication costs and…
We study a new aggregation operator for gradients coming from a mini-batch for stochastic gradient (SG) methods that allows a significant speed-up in the case of sparse optimization problems. We call this method AdaBatch and it only requires a few lines of code change compared to regular mini-batch SGD algorithms. We p…
Private Aggregation in Hierarchical Wireless Federated Learning with Partial and Full Collusioncs.LG
This paper addresses privacy in federated learning with wireless clients and base stations.
problem Privacy of clients' data in federated learning with hierarchical wireless architecture.
method Derives communication cost limits and introduces private aggregation schemes tailored for hierarchical wireless systems.
result Private aggregation schemes reduce communication costs by multiplicative factors compared to information-theoretic limits.
GRAIN: Group Aggregation via Min-Norm Objective
problem Learning instability in large models
method Replacing mean aggregation with min-norm convex combination
result Improves performance and reduces variance
This paper optimizes MDP policies for efficient state aggregation.
problem Optimizing policies in aggregated Markov chains while preserving optimal performance.
method Homomorphic mappings to establish optimal policy equivalence and derive performance bounds.
result Developed HPG and EBHPG methods for efficient aggregation and policy optimization.
Recent advances in machine learning have largely benefited from the massive accessible training data. However, large-scale data sharing has raised great privacy concerns. In this work, we propose a novel privacy-preserving data Generative model based on the PATE framework (G-PATE), aiming to train a scalable differenti…
The paper proposes a method to learn differentially private variational autoencoders with term-wise gradient aggregation.
problem Learning variational autoencoders with differential privacy constraints and multiple divergences.
method Term-wise Differentially Private SGD (DP-SGD) that crafts randomized gradients for each loss term, keeping sensitivity at O(1).
result The method reduces the amount of noise needed for differential privacy, allowing better learning.
To improve the resilience of distributed training to worst-case, or Byzantine node failures, several recent approaches have replaced gradient averaging with robust aggregation methods. Such techniques can have high computational costs, often quadratic in the number of compute nodes, and only have limited robustness gua…
Federated learning is a distributed learning method to train a shared model by aggregating the locally-computed gradient updates. In federated learning, bandwidth and privacy are two main concerns of gradient updates transmission. This paper proposes an end-to-end encrypted neural network for gradient updates transmiss…
This paper introduces a family of local feature aggregation functions and a novel method to estimate their parameters, such that they generate optimal representations for classification (or any task that can be expressed as a cost function minimization problem). To achieve that, we compose the local feature aggregation…
We propose three new robust aggregation rules for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilie…
A framework for federated adversarial learning with convergence analysis.
problem Unique vulnerabilities to adversarial attacks in federated learning.
method Formulates a general federated adversarial learning framework with inner and outer loops for client-side adversarial training and server-side model aggregation.
result The minimum loss under the proposed algorithm can converge to ε with chosen learning rate and communication rounds.
Two novel algorithms improve distributed machine learning in the presence of Byzantine adversaries.
problem Improving distributed machine learning in the presence of Byzantine adversaries.
method Two novel stochastic gradient descent algorithms, ByGARS and ByGARS++, using reputation scores for gradient aggregation.
result Robust to any number of multiplicative noise Byzantine adversaries and converge for strongly convex loss functions.
Robust algorithm for distributed optimization resistant to Byzantine failures.
problem Resilient optimization in the presence of unreliable agents.
method Temporal and spatial robust aggregation, gradient normalization.
result Convergence for strongly convex and non-convex functions.
We consider the problem of distributed statistical machine learning in adversarial settings, where some unknown and time-varying subset of working machines may be compromised and behave arbitrarily to prevent an accurate model from being learned. This setting captures the potential adversarial attacks faced by Federate…
We focus on the commonly used synchronous Gradient Descent paradigm for large-scale distributed learning, for which there has been a growing interest to develop efficient and robust gradient aggregation strategies that overcome two key system bottlenecks: communication bandwidth and stragglers' delays. In particular, R…
Proposes a method for private aggregation in heterogeneous federated learning.
problem Ensuring resilience to Byzantine clients and maintaining client data privacy in federated learning with heterogeneous data.
method Careful co-design of verifiable secret sharing, secure aggregation, and private information retrieval scheme.
result Achieves information-theoretic privacy guarantees and Byzantine resilience under data heterogeneity.
DeeperGCN tackles deep GCNs by overcoming vanishing gradient and over-smoothing issues.
problem Vanishing gradient, over-smoothing, and over-fitting issues in deep GCNs.
method DeeperGCN uses differentiable generalized aggregation functions and a novel normalization layer (MsgNorm) to train deep GCNs.
result DeeperGCN significantly boosts performance on large-scale graph learning tasks.
In this paper, we explore a general Aggregated Gradient Langevin Dynamics framework (AGLD) for the Markov Chain Monte Carlo (MCMC) sampling. We investigate the nonasymptotic convergence of AGLD with a unified analysis for different data accessing (e.g. random access, cyclic access and random reshuffle) and snapshot upd…
FedNAG improves federated learning accuracy and reduces training time.
problem Efficiency of federated learning with gradient descent.
method Nesterov Accelerated Gradient (NAG) applied to federated learning (FL) with additional momentum and model aggregation.
result FedNAG increases learning accuracy by 3-24% and reduces training time by 11-70%.
This paper deals with distributed finite-sum optimization for learning over networks in the presence of malicious Byzantine attacks. To cope with such attacks, most resilient approaches so far combine stochastic gradient descent (SGD) with different robust aggregation rules. However, the sizeable SGD-induced stochastic…
More frequent model updates in FL increase generalization error.
problem Negative impact of frequent communication on FL model generalization.
method Analyzed the effect of the number of rounds of model aggregation on generalization error.
result Generalization error increases with more frequent model updates.
Meta-strategy learns tuning parameters for online learning methods.
problem Difficulty in setting tuning parameters for online learning methods.
method Meta-learning approach to learn parameters from past tasks.
result Meta-strategy improves on learning each task in isolation.
This paper accelerates distributed convex optimization by mitigating ill-conditioning issues.
problem Distributed convex optimization with ill-conditioned aggregate cost functions.
method Iterative pre-conditioning technique to improve convergence rate and stability.
result The proposed algorithm converges linearly with improved convergence rate and superlinearly under certain conditions.
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.
Method learns CTMC models from steady-state data, predicting unseen states.
problem Learning CTMC models from aggregate steady-state statistics without sequence examples.
method ∞-SGD, a stochastic gradient descent method that avoids infinite sums.
result Successfully learns CTMC models and predicts unseen states.
Randomized gradient-based ensemble improves prediction accuracy.
problem Improving prediction accuracy in machine learning.
method Randomization and gradient-based aggregation of weakly-correlated estimators.
result The method outperforms existing techniques in terms of increased accuracy.
Proposes a method to improve Byzantine-robustness in compressed federated learning.
problem Byzantine-robustness in compressed federated learning.
method Gradient difference compression and stochastic average gradient algorithm (SAGA).
result The proposed method reaches a neighborhood of the optimal solution at a linear convergence rate.
Momentum is a simple and widely used trick which allows gradient-based optimizers to pick up speed along low curvature directions. Its performance depends crucially on a damping coefficient . Large values can potentially deliver much larger speedups, but are prone to oscillations and instability; hence one typic…
New method improves training stochastic neural networks with tighter guarantees.
problem Training stochastic neural networks with provable guarantees.
method Developed partially-aggregated estimators and reformulated PAC-Bayesian bounds.
result Derives a differentiable objective leading to tighter generalisation guarantees.
HCBM improves deep learning explainability by non-linear concept aggregation.
problem Lack of explainable and accurate predictions in deep learning for high-stake decisions.
method Introduce Hoeffding Concept Bottleneck Models (HCBM) using Hoeffding functional decomposition of gradient-boosted trees for non-linear and sparse concept aggregation.
result HCBM outperforms standard linear CBM and is robust to interconcept leakage.