More Like this

1. SQuARM-SGD: Communication-Efficient Momentum SGD for Decentralized Optimization

   Singh, Navjot; Data, Deepesh; George, Jemin; Diggavi, Suhas N. (July 2021, IEEE International Symposium on Information Theory (ISIT))

   null (Ed.)

   In this paper, we study communication-efficient decentralized training of large-scale machine learning models over a network. We propose and analyze SQuARM-SGD, a decentralized training algorithm, employing momentum and compressed communication between nodes regulated by a locally computable triggering rule. In SQuARM-SGD, each node performs a fixed number of local SGD (stochastic gradient descent) steps using Nesterov's momentum and then sends sparisified and quantized updates to its neighbors only when there is a significant change in its model parameters since the last time communication occurred. We provide convergence guarantees of our algorithm for strongly-convex and non-convex smooth objectives. We believe that ours is the first theoretical analysis for compressed decentralized SGD with momentum updates. We show that SQuARM-SGD converges at rate O(1/nT) for strongly-convex objectives, while for non-convex objectives it converges at rate O(1/√nT), thus matching the convergence rate of \emphvanilla distributed SGD in both these settings. We corroborate our theoretical understanding with experiments and compare the performance of our algorithm with the state-of-the-art, showing that without sacrificing much on the accuracy, SQuARM-SGD converges at a similar rate while saving significantly in total communicated bits. 

   more » « less
2. Projection-free nonconvex stochastic optimization on Riemannian manifolds

   https://doi.org/10.1093/imanum/drab066  

   Weber, Melanie; Sra, Suvrit (September 2021, IMA Journal of Numerical Analysis)

   Abstract We study stochastic projection-free methods for constrained optimization of smooth functions on Riemannian manifolds, i.e., with additional constraints beyond the parameter domain being a manifold. Specifically, we introduce stochastic Riemannian Frank–Wolfe (Fw) methods for nonconvex and geodesically convex problems. We present algorithms for both purely stochastic optimization and finite-sum problems. For the latter, we develop variance-reduced methods, including a Riemannian adaptation of the recently proposed Spider technique. For all settings, we recover convergence rates that are comparable to the best-known rates for their Euclidean counterparts. Finally, we discuss applications to two classic tasks: the computation of the Karcher mean of positive definite matrices and Wasserstein barycenters for multivariate normal distributions. For both tasks, stochastic Fw methods yield state-of-the-art empirical performance. 

   more » « less
3. Level constrained first order methods for function constrained optimization

   https://doi.org/10.1007/s10107-024-02057-4  

   Boob, Digvijay; Deng, Qi; Lan, Guanghui (March 2024, Mathematical Programming)

   Abstract We present a new feasible proximal gradient method for constrained optimization where both the objective and constraint functions are given by summation of a smooth, possibly nonconvex function and a convex simple function. The algorithm converts the original problem into a sequence of convex subproblems. Formulating those subproblems requires the evaluation of at most one gradient-value of the original objective and constraint functions. Either exact or approximate subproblems solutions can be computed efficiently in many cases. An important feature of the algorithm is the constraint level parameter. By carefully increasing this level for each subproblem, we provide a simple solution to overcome the challenge of bounding the Lagrangian multipliers and show that the algorithm follows a strictly feasible solution path till convergence to the stationary point. We develop a simple, proximal gradient descent type analysis, showing that the complexity bound of this new algorithm is comparable to gradient descent for the unconstrained setting which is new in the literature. Exploiting this new design and analysis technique, we extend our algorithms to some more challenging constrained optimization problems where (1) the objective is a stochastic or finite-sum function, and (2) structured nonsmooth functions replace smooth components of both objective and constraint functions. Complexity results for these problems also seem to be new in the literature. Finally, our method can also be applied to convex function constrained problems where we show complexities similar to the proximal gradient method. 

   more » « less
4. SPARQ-SGD: Event-Triggered and Compressed Communication in Decentralized Optimization

   https://doi.org/10.1109/CDC42340.2020.9303828  

   Singh, Navjot; Data, Deepesh; George, Jemin; Diggavi, Suhas (December 2020, IEEE Control and Decision Conference (CDC))

   In this paper, we propose and analyze SPARQSGD, an event-triggered and compressed algorithm for decentralized training of large-scale machine learning models over a graph. Each node can locally compute a condition (event) which triggers a communication where quantized and sparsified local model parameters are sent. In SPARQ-SGD, each node first takes a fixed number of local gradient steps and then checks if the model parameters have significantly changed compared to its last update; it communicates further compressed model parameters only when there is a significant change, as specified by a (design) criterion. We prove that SPARQ-SGD converges as O(1/nT ) and O(1/√nT ) in the strongly-convex and non-convex settings, respectively, demonstrating that aggressive compression, including event-triggered communication, model sparsification and quantization does not affect the overall convergence rate compared to uncompressed decentralized training; thereby theoretically yielding communication efficiency for `free'. We evaluate SPARQ-SGD over real datasets to demonstrate significant savings in communication bits over the state-of-the-art. 

   more » « less
5. Shuffled model of differential privacy in federated learnin

   Girgis, Antonious M; Data, Deepesh; Diggavi, Suhas; Kairouz, Peter; and Suresh, Theerta. (January 2021, International Conference on Artificial Intelligence and Statistics, AISTATS)

   We consider a distributed empirical risk minimization (ERM) optimization problem with communication efficiency and privacy requirements, motivated by the federated learn- ing (FL) framework. We propose a distributed communication-efficient and local differentially private stochastic gradient descent (CLDP-SGD) algorithm and analyze its communication, privacy, and convergence trade-offs. Since each iteration of the CLDP- SGD aggregates the client-side local gradients, we develop (optimal) communication-efficient schemes for mean estimation for several lp spaces under local differential privacy (LDP). To overcome performance limitation of LDP, CLDP-SGD takes advantage of the inherent privacy amplification provided by client sub- sampling and data subsampling at each se- lected client (through SGD) as well as the recently developed shuffled model of privacy. For convex loss functions, we prove that the proposed CLDP-SGD algorithm matches the known lower bounds on the centralized private ERM while using a finite number of bits per iteration for each client, i.e., effectively get- ting communication efficiency for “free”. We also provide preliminary experimental results supporting the theory. 

   more » « less