This work improves SGD minibatch sampling using determinantal point processes based on orthogonal polynomials.
problem Improving variance reduction in stochastic gradient descent (SGD) for large datasets.
method Orthogonal polynomial-based determinantal point processes for sampling minibatches in SGD.
result DPP minibatches lead to a smaller mean square approximation error than uniform minibatches.
Paper proposes a method to estimate variance reduction in DNN training using importance sampling.
problem Challenges in assessing variance reduction during DNN training using importance sampling.
method Proposes a method for estimating variance reduction using minibatches sampled under importance sampling.
result Demonstrates consistent reduction in variance, improved training efficiency, and enhanced model accuracy.
Unified analysis of stochastic gradient methods for convex and smooth optimization.
problem Minimizing composite convex and smooth functions.
method Unified convergence analysis of various stochastic gradient methods.
result Unified convergence rates for a variety of methods including proximal SGD, variance reduced methods, quantization, and coordinate descent.
Stochastic Gradient Descent (SGD) is a popular optimization method which has been applied to many important machine learning tasks such as Support Vector Machines and Deep Neural Networks. In order to parallelize SGD, minibatch training is often employed. The standard approach is to uniformly sample a minibatch at each…
Adaptive batch sizes improve local gradient methods in distributed training.
problem Communication bottlenecks in distributed deep learning.
method Adaptive batch size strategies for local gradient methods.
result Adaptive batch sizes reduce minibatch gradient variance and improve training efficiency.
Stochastic gradient Markov Chain Monte Carlo (SG-MCMC) has been developed as a flexible family of scalable Bayesian sampling algorithms. However, there has been little theoretical analysis of the impact of minibatch size to the algorithm's convergence rate. In this paper, we prove that under a limited computational bud…
We investigate a local reparameterizaton technique for greatly reducing the variance of stochastic gradients for variational Bayesian inference (SGVB) of a posterior over model parameters, while retaining parallelizability. This local reparameterization translates uncertainty about global parameters into local noise th…
Contrastive Divergence (CD) and Persistent Contrastive Divergence (PCD) are popular methods for training the weights of Restricted Boltzmann Machines. However, both methods use an approximate method for sampling from the model distribution. As a side effect, these approximations yield significantly different biases and…
This paper studies communication efficiency in federated learning by optimizing the sum-rate-distortion function for indirect multiterminal source coding.
problem Indirect multiterminal source coding in federated learning where edge devices send noisy gradients to the server.
method Analyzes the rate region for the quadratic vector Gaussian CEO problem under unbiased estimator and derives an explicit formula for the sum-rate-distortion function.
result Derives an explicit formula for the sum-rate-distortion function in the special case of identical gradients over edge devices.
New DPP kernels improve minibatch efficiency for large datasets.
problem Efficiently generating minibatches from large datasets.
method Wavelet-based DPPs and novel discrete conversion methods.
result Improved minibatch efficiency with low-rank decompositions.
Although stochastic gradient descent (SGD) is a driving force behind the recent success of deep learning, our understanding of its dynamics in a high-dimensional parameter space is limited. In recent years, some researchers have used the stochasticity of minibatch gradients, or the signal-to-noise ratio, to better char…
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.
Develops minibatch stochastic proximal gradient for large-scale learning models.
problem Finding optimal predictors with complex regularizers in large-scale learning models.
method Minibatch variants of stochastic proximal gradient algorithm for composite objective functions.
result Minibatch size N after O(Nε1) iterations achieves ε−suboptimality in expected quadratic distance. We present novel minibatch stochastic optimization methods for empirical risk minimization problems, the methods efficiently leverage variance reduced first-order and sub-sampled higher-order information to accelerate the convergence speed. For quadratic objectives, we prove improved iteration complexity over state-of-…
New minibatching strategy reduces stochastic gradient bias in optimisation.
problem Reducing bias in stochastic gradient descent.
method Symmetric Minibatching Strategy combined with momentum.
result Reduced stochastic gradient bias from O(h2) to O(h4). DP-PCA improves privacy in PCA computations with optimal statistical error.
problem Differentially private principal component analysis with sub-linear sample complexity.
method Private minibatch gradient ascent with private mean estimation.
result Achieves optimal statistical error rates for sub-Gaussian data with n=ildeO(d) samples. Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Mini-batch SGD is one of the most popular stochastic optimization methods in training deep networks, it shows a slow convergence rate due to the larg…
Doubly SGD improves convergence for intractable objective optimization.
problem Optimizing objectives in sum of intractable expectations.
method Doubly SGD with doubly stochastic gradients and independent minibatching.
result Established convergence of doubly SGD under general conditions, including dependent component gradient estimators.
Behavior cloning training instabilities amplified by SGD noise over long horizons.
problem Training instabilities in behavior cloning with deep neural networks.
method Empirical dissection of minibatch SGD updates and their effects on long-horizon rewards.
result Exponential moving average (EMA) of iterates effectively mitigates gradient variance amplification (GVA).
This paper analyzes minibatch optimal transport distances and their applications.
problem Optimal transport distances are complex and impractical for large datasets.
method Extended analysis of minibatch optimal transport distances, focusing on various kernels and debiased functions.
result Minibatch optimal transport distances are unbiased estimators and have statistical and optimisation properties.
We consider the fundamental problem in non-convex optimization of efficiently reaching a stationary point. In contrast to the convex case, in the long history of this basic problem, the only known theoretical results on first-order non-convex optimization remain to be full gradient descent that converges in $O(1/\varep…
SGD converges to global minimum for structured non-convex functions.
problem Optimizing non-convex functions using SGD with slow convergence rates.
method Convergence theorems for SGD on structured non-convex functions, including Quasar and PL conditions.
result SGD converges to global minimum for specific non-convex functions under certain conditions.
Paper proves minibatch SGD for GP inference converges and improves generalization.
problem Theoretical understanding and practical use of SGD for correlated samples in Gaussian process inference.
method Proves minibatch SGD converges to a critical point with rate O(1/K) for K iterations, under certain kernel conditions.
result Minibatch SGD for GP inference improves generalization and reduces computational burden.
EVA adapts LoRA for faster, more efficient fine-tuning.
problem Fast and efficient fine-tuning of large models for specific tasks.
method EVA uses directions capturing most activation variance for initialization, maximizing gradient signal and reducing parameters.
result EVA achieves faster convergence and higher average scores across tasks, reducing parameters.
Improved algorithm reduces stochastic gradient complexity for large-scale learning problems.
problem High stochastic gradient complexity for large-scale learning problems.
method Hybrid Stochastic-Deterministic Minibatch Proximal Gradient (HSDMPG) algorithm.
result Achieves nearly optimal generalization in less than a single pass over data.
It is well known that, for most datasets, the use of large-size minibatches for Stochastic Gradient Descent (SGD) typically leads to slow convergence and poor generalization. On the other hand, large minibatches are of great practical interest as they allow for a better exploitation of modern GPUs. Previous literature …
Recent work has argued that stochastic gradient descent can approximate the Bayesian uncertainty in model parameters near local minima. In this work we develop a similar correspondence for minibatch natural gradient descent (NGD). We prove that for sufficiently small learning rates, if the model predictions on the trai…
Anytime MiniBatch speeds up online distributed optimization by handling slow nodes.
problem Mitigating the impact of slow nodes (stragglers) in distributed optimization.
method Proposes an online distributed optimization method that averages minibatch gradients via consensus rounds.
result Prevents stragglers from slowing progress without wasting work.
New method improves convergence of SPP for convex optimization problems.
problem Stochastic optimization and robustness to SGD.
method Minibatch Stochastic Proximal Point (M-SPP) method with stability analysis.
result M-SPP achieves faster convergence rates under smoothness and quadratic growth conditions.
Minibatching is a very well studied and highly popular technique in supervised learning, used by practitioners due to its ability to accelerate training through better utilization of parallel processing power and reduction of stochastic variance. Another popular technique is importance sampling -- a strategy for prefer…
New sampling technique improves KGC model performance.
problem Ignoring entity neighbors in minibatches affects KGC model training.
method Random-walk based minibatch sampling.
result Proposed method achieves state-of-the-art performance on DB100K.
SGLRW improves robustness of stochastic gradient MCMC methods.
problem Sensitivity to minibatch size and gradient noise in stochastic-gradient MCMC methods.
method Proposes Stochastic Gradient Lattice Random Walk (SGLRW) with lattice-based discretization.
result SGLRW remains stable in regimes where SGLD fails, including heavy-tailed gradient noise.
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.
Unbalanced minibatch Optimal Transport improves domain adaptation performance.
problem Optimal transport distances are computationally expensive for large datasets.
method Use unbalanced minibatch Optimal Transport to estimate distances over subsets of data.
result Unbalanced Optimal Transport leads to better domain adaptation results.
GT-SARAH optimizes decentralized non-convex problems with recursive variance reduction.
problem Decentralized non-convex optimization of N functions over a network. method Stochastic first-order gradient method with SARAH variance reduction and gradient tracking.
result Achieves ε-accurate first-order stationary point with improved gradient complexity. A new method for distributed optimization reduces communication rounds without minibatches.
problem Efficient training in distributed machine learning with different data distributions.
method A primal-dual method (GA-MSGD) applied to the Lagrangian of distributed optimization.
result Achieves linear convergence in communication rounds for strongly convex objectives.
New algorithm reduces bias and variance in weighted least-squares solutions.
problem Inconsistent linear least-squares problems with rapidly decaying singular values.
method Regularized block Kaczmarz (ReBlocK) algorithm.
result ReBlocK outperforms RBK and minibatch SGD for inconsistent problems.
New convergence bounds for shuffling-based SGD methods in distributed learning.
problem Analyzing the performance of shuffling-based variants of SGD in distributed learning.
method Study of minibatch and local Random Reshuffling methods, proving convergence bounds and lower bounds.
result Shuffling-based variants converge faster than with-replacement sampling methods, and the bounds are tight.
Improved sampling for Bayesian neural networks reduces vanishing acceptance rates and increases predictive accuracy.
problem Sampling inefficiency in Bayesian neural networks, especially with deep architectures and large datasets.
method Approximate blocked Gibbs sampling to partition and sample subgroups of parameters.
result Increased predictive accuracy and quantification of predictive uncertainty in classification tasks.
Study on the noise in SGD minibatches near local minima.
problem Understanding the noise in SGD minibatches near local minima.
method Detailed analysis of SGD noise in linear regression and derivation of a general formula for different types of minima.
result Provides insight into the stability of training neural networks and suggests large learning rates can help generalization.
Study on gradient complexity of private optimization with private oracles.
problem Analyzing the efficiency of differentially private optimization algorithms.
method Lower bounds on the number of first-order oracle queries for private optimization.
result Lower bounds on the number of queries for private optimization algorithms, showing a dimension-dependent runtime penalty.
Optimal transport distances are powerful tools to compare probability distributions and have found many applications in machine learning. Yet their algorithmic complexity prevents their direct use on large scale datasets. To overcome this challenge, practitioners compute these distances on minibatches {\em i.e.} they a…
Differentiable learning via SGD and GD can simulate various learning problems, depending on precision and minibatch size.
problem Understanding the power of differentiable learning via SGD and GD compared to statistical query (SQ) learning.
method Comparing the learning power of SGD and GD on population and empirical losses with statistical query learning.
result The learning power of SGD and GD depends on the precision of gradient calculations relative to the minibatch size or sample size.
CD algorithm achieves near-optimal convergence rate for unnormalized models.
problem Training unnormalized models with high efficiency.
method Non-asymptotic analysis of contrastive divergence algorithm.
result CD can achieve O(n−1/2) convergence rate under regularity assumptions. A new algorithm improves GAN training stability and performance.
problem Training GANs is difficult due to variance and rotational dynamics.
method Proposes Lookahead-Minmax algorithm for minmax optimization.
result Significant improvement in GAN performance and stability.
RAD estimates gradients with less memory, faster than small batch sizes.
problem Training deep models with stochastic gradient descent requires exact gradients, but they are not needed.
method Developed a framework for randomized automatic differentiation (RAD) to compute unbiased gradient estimates with reduced memory.
result RAD converges in fewer iterations than using a small batch size for feedforward networks and similar number for recurrent networks.
New approach speeds up optimization with repeated gradient steps on same batch.
problem Performance bottlenecks in massive parallel pipelines with large batch sizes.
method Data echoing, taking repeated gradient steps on the same batch.
result Data echoing affords speedups on curvature-dominated part of convergence rate.
We present an approach towards convex optimization that relies on a novel scheme which converts online adaptive algorithms into offline methods. In the offline optimization setting, our derived methods are shown to obtain favourable adaptive guarantees which depend on the harmonic sum of the queried gradients. We furth…