The thesis clarifies when local updates outperform centralized methods in heterogeneous data environments.
problem Understanding when local updates are more effective than centralized or mini-batch methods in distributed optimization.
method Fine-grained consensus-error-based analysis framework, focusing on bounded second-order heterogeneity and third-order smoothness.
result Local updates outperform centralized or mini-batch methods under realistic models of data heterogeneity.
Local adaptive methods in FL can accelerate convergence but introduce bias, which is corrected.
problem The effect of using adaptive optimization methods for local updates in federated learning.
method Proposed correction techniques to overcome the bias introduced by local adaptive methods.
result Correction techniques can achieve faster convergence and higher test accuracy than baseline methods.
Local update methods' performance depends on learning rates, affecting convergence rates and alignment with true loss.
problem The performance of local update methods in federated learning and meta-learning is sensitive to learning rates.
method Proved that local update methods perform SGD on a surrogate loss function, characterized the surrogate loss, and derived convergence rates.
result Proper learning rate tuning is crucial for near-optimal behavior in communication-limited settings.
LD-SGD improves communication in decentralized SGD.
problem Efficiently combining local updates and decentralized communication.
method Proposes LD-SGD integrating local updates and decentralized SGD, with a convergence analysis.
result LD-SGD converges to a critical point for non-convex objectives with non-identically distributed data.
A new method reduces communication costs in decentralized optimization.
problem Decentralized optimization with non-convex cost functions.
method LU-GT method with local updates.
result LU-GT achieves the same communication complexity as Federated Learning and maintains solution quality.
FedShuffle improves local updates in FL, especially with data imbalance.
problem Data imbalance in FL leads to different clients performing different numbers of local updates.
method FedShuffle incorporates random reshuffling, data imbalance, and client sampling.
result FedShuffle improves upon FL methods that assume homogeneous updates in heterogeneous setups.
Paper analyzes ensemble Kalman updates for effective dimension and localization.
problem Why small ensemble sizes work well in inverse problems and data assimilation.
method Non-asymptotic analysis of ensemble Kalman updates, focusing on effective dimension and localization.
result Rigorously explains why a small ensemble size is sufficient when prior covariance has moderate effective dimension.
Unified analysis for decentralized SGD across various topologies and updates.
problem Analysis of decentralized SGD methods with changing topologies and local updates.
method Unified convergence analysis covering local SGD updates and adaptive network topology.
result Universal convergence rates for smooth problems, interpolating between heterogeneous and iid-data settings.
Optimal client sampling reduces communication in federated learning.
problem Efficiently aggregate model updates from distributed clients in federated learning.
method Model weights as an Ornstein-Uhlenbeck process to estimate uncommunicated updates; optimal client sampling strategy.
result Significant reduction in communication with competitive or superior performance.
Develops local population-risk certificates for model updates
problem Model updates in machine learning
method Certify population-risk increments around a model
result Certified upper endpoint yields a risk-controlled update rule
New insights into convergence and accuracy trade-offs in federated and meta-learning.
problem Understanding the trade-offs between convergence and accuracy in federated and meta-learning.
method Generalized local update methods, proving equivalence to first-order optimization on a surrogate loss.
result Novel convergence rates and insights into the importance of algorithmic choices in communication-limited settings.
A networked learning method for correlated data outperforms federated learning in precision.
problem Estimating models from correlated data distributed across a network.
method Local linear model estimation with network regularization and information exchange.
result The weighted ensemble average estimate converges faster and more precisely than federated learning.
Proposes glocal hypergradient estimation for hyperparameter optimization.
problem Combining reliability and efficiency in hyperparameter optimization.
method Uses Koopman operator theory to approximate global hypergradients from local ones.
result Achieves both reliability and efficiency in hyperparameter optimization.
A new method automatically and dynamically sets learning rates in deep learning.
problem Determining the appropriate learning rate in deep learning tasks is challenging and often subjective.
method Local Quadratic Approximation (LQA) to automatically and dynamically set learning rates.
result The proposed method leads to nearly optimal learning rates in a computationally efficient way.
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.
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. FedPAQ improves federated learning efficiency by averaging and quantizing updates.
problem Communication bottlenecks and scalability issues in federated learning.
method Periodic averaging, partial device participation, and quantized message-passing.
result FedPAQ achieves near-optimal theoretical guarantees and demonstrates communication-computation tradeoffs.
New framework provides privacy guarantees for practical federated learning.
problem Inadequate privacy guarantees for federated learning due to restrictive assumptions.
method Fed- α \alpha α -NormEC, integrating multiple local updates, partial client participation, and standard assumptions. result Provably convergent and differentially private federated learning framework.
FedElasticNet reduces communication costs and handles client drift in FL.
problem Expensive communication costs and client drift issues in federated learning.
method Leverages elastic net regularizers to sparsify local updates and limit client drift.
result FedElasticNet effectively resolves communication cost and client drift problems.
We present ARU, an Adaptive Recurrent Unit for streaming adaptation of deep globally trained time-series forecasting models. The ARU combines the advantages of learning complex data transformations across multiple time series from deep global models, with per-series localization offered by closed-form linear models. Un…
Distributed optimization often consists of two updating phases: local optimization and inter-node communication. Conventional approaches require working nodes to communicate with the server every one or few iterations to guarantee convergence. In this paper, we establish a completely different conclusion that each node…
Locally private reinforcement learning protects individual environments from reverse engineering.
problem Protecting private information in distributed reinforcement learning environments.
method Locally differentially private algorithms that protect local agents' models from adversarial reverse engineering.
result Demonstrated that the proposed algorithm performs well under local differential privacy (LDP).
Actor-critic methods solve reinforcement learning problems by updating a parameterized policy known as an actor in a direction that increases an estimate of the expected return known as a critic. However, existing actor-critic methods only use values or gradients of the critic to update the policy parameter. In this pa…
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…
A new update rule for deep reinforcement learning reduces learning variance and variance in reference signals.
problem Learning variance and incorrect reference signals in deep reinforcement learning.
method t-soft update method inspired by student-t distribution, which reduces extreme updates and accelerates similar updates.
result The t-soft update method outperforms conventional methods in terms of return and variance in PyBullet robotics simulations.
We show that deep networks can be trained using Hebbian updates yielding similar performance to ordinary back-propagation on challenging image datasets. To overcome the unrealistic symmetry in connections between layers, implicit in back-propagation, the feedback weights are separate from the feedforward weights. The f…
We investigate finite-time decoupled convergence in nonlinear two-time-scale stochastic approximation.
problem Achieving decoupled convergence in nonlinear two-time-scale stochastic approximation.
method Nested local linearity assumption, suitable step size selection, convergence analysis of matrix cross term, fourth-order moment convergence rates.
result Finite-time decoupled convergence rates can be achieved in nonlinear two-time-scale stochastic approximation with proper step size selection.
Paper tackles free rider attacks in federated learning.
problem Clients without local data can cheat for rewards.
method Proposes STD-DAGMM for anomaly detection of model parameters.
result STD-DAGMM effectively detects free rider attacks.
Inference problems in graphical models are often approximated by casting them as constrained optimization problems. Message passing algorithms, such as belief propagation, have previously been suggested as methods for solving these optimization problems. However, there are few convergence guarantees for such algorithms…
A new method for efficient neural network fine-tuning using queryable low-rank update atoms.
problem Rigidity of static low-rank adaptation methods when input and depth-wise computation vary.
method A shared queryable memory of low-rank update atoms, allowing dynamic and context-sensitive adaptation.
result Improves final test performance and training stability compared to standard low-rank adaptation.
A new graph neural network (NBA-GNN) avoids revisiting nodes to improve accuracy.
problem Redundancy in graph neural network updates causes over-squashing and inaccurate recognition.
method Proposes non-backtracking graph neural networks (NBA-GNN) that update messages without revisiting nodes.
result The NBA-GNN alleviates over-squashing and improves performance on graph benchmarks.
New algorithm reduces FL sample and communication costs.
problem Optimizing FL for minimal samples and rounds.
method Stochastic two-sided momentum algorithm.
result Achieves near-optimal sample and communication complexities.
We study active learning (AL) based on Gaussian Processes (GPs) for efficiently enumerating all of the local minimum solutions of a black-box function. This problem is challenging due to the fact that local solutions are characterized by their zero gradient and positive-definite Hessian properties, but those derivative…
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.
Biological neural network mimics CCA for multi-channel data.
problem Implementing CCA in a biologically plausible neural network.
method Derive an online CCA algorithm with local synaptic updates for multi-compartmental neurons.
result The derived neural network architecture and synaptic updates resemble cortical pyramidal neuron behavior.
EP learns like BPTT but with local weight updates.
problem Existing EP lacks a local time learning rule.
method C-EP updates weights simultaneously with neuron dynamics.
result C-EP follows BPTT gradients and performs well.
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.
We describe k k k -MLE, a fast and efficient local search algorithm for learning finite statistical mixtures of exponential families such as Gaussian mixture models. Mixture models are traditionally learned using the expectation-maximization (EM) soft clustering technique that monotonically increases the incomplete (expec…
Framework for safely updating machine learning models.
problem Continuous updates to machine learning models can lead to unintended consequences.
method Formalizes the problem as computing the largest locally invariant domain (LID), uses tractable primal-dual formulation.
result Matches or exceeds heuristic baselines for avoiding forgetting while providing formal safety guarantees.
Improved ADMM for convex distributed learning with differential privacy.
problem Privacy concerns in distributed learning with sensitive data.
method Approximate multi-step ADMM with calibrated noise.
result Higher utility and error bounds asymptotic to state-of-the-art.
This paper evaluates and compares gradient leakage attacks in federated learning.
problem Gradient leakage attacks compromise client privacy in federated learning.
method Formal and experimental analysis of gradient leakage attacks, evaluation of attack effectiveness and cost.
result Gradient leakage attacks can reconstruct private local training data from shared parameter updates.
New method uses randomized sparse neural networks to solve time-dependent PDEs more accurately and efficiently.
problem Numerical challenges in training neural networks sequentially in time to solve time-dependent PDEs.
method Introduces Neural Galerkin schemes that update randomized sparse subsets of network parameters at each time step.
result Up to two orders of magnitude more accurate and two orders of magnitude faster than dense update schemes.
Existing nonnegative matrix factorization methods focus on learning global structure of the data to construct basis and coefficient matrices, which ignores the local structure that commonly exists among data. In this paper, we propose a new type of nonnegative matrix factorization method, which learns local similarity …
We introduce a new local regret framework for non-convex models in dynamic environments.
problem Challenges in online forecasting for non-convex models with frequent updates and concept drift.
method We propose a novel local regret framework and a time-smoothed gradient update rule.
result Our approach yields more stable, robust, and computationally efficient forecasting compared to state-of-the-art methods.
A common divide-and-conquer approach for Bayesian computation with big data is to partition the data, perform local inference for each piece separately, and combine the results to obtain a global posterior approximation. While being conceptually and computationally appealing, this method involves the problematic need t…
We introduce novel variants of momentum by incorporating the variance of the stochastic loss function. The variance characterizes the confidence or uncertainty of the local features of the averaged loss surface across the i.i.d. subsets of the training data defined by the mini-batches. We show two applications of the g…
Local SGD with periodic averaging achieves faster convergence with less communication.
problem Communication overhead in distributed optimization.
method Local SGD with periodic averaging, Polyak-Łojasiewicz condition, adaptive synchronization.
result Local SGD can achieve linear speed up with fewer communication rounds, especially for non-strongly convex functions.
A new algorithm reduces training time for distributed machine learning by dynamically assigning backup workers.
problem Time-consuming synchronization phase due to slow workers (stragglers).
method Dynamic allocation of backup workers to minimize waiting time.
result Achieves linear speedup in convergence performance with more workers.