One-shot algorithm for feature-distributed kernel PCA reduces communication costs.
problem Efficiently perform kernel PCA in distributed computing environments.
method Inspired by dual relationship between sample-distributed and feature-distributed scenarios, proposes a one-shot algorithm for feature-distributed kernel PCA.
result The algorithm provides high-quality results with low communication costs, especially when eigenvalues decay fast.
Paper develops a new algorithm for distribution regression with optimal learning rates.
problem Distribution regression with limited second-stage samples.
method Multi-penalty regularization in a reproducing kernel Hilbert space.
result Derives optimal learning rates for distribution regression.
Distributed machine learning algorithms enable learning of models from datasets that are distributed over a network without gathering the data at a centralized location. While efficient distributed algorithms have been developed under the assumption of faultless networks, failures that can render these algorithms nonfu…
New algorithms for efficient return distribution approximation in reinforcement learning.
problem Efficiently approximating unknown return distributions in reinforcement learning.
method Introduced novel distributional dynamic programming algorithms for arbitrary probabilistic reward mechanisms.
result Proved error bounds for the algorithms in Wasserstein and Kolmogorov--Smirnov distances.
Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yield state-of-the-art empirical performance. This was demonstrated by the recently proposed C51 algorithm, based on categorical distributiona…
We analyze reinforcement learning algorithms using a distributional approach.
problem Theoretical analysis of reinforcement learning algorithms for constant step-sizes.
method Distributional approach to theoretical analyses of reinforcement learning algorithms.
result TD(λ) and Q-Learning have contractive update rules in the space of distributions of functions, leading to exponentially fast convergence. Greedy algorithm achieves sublinear regret for various distributions.
problem Efficient performance of greedy algorithms in linear contextual bandit problems.
method Introduced Local Anti-Concentration (LAC) condition to ensure sublinear regret.
result Greedy algorithm achieves O(polylogT) cumulative expected regret. Paper proposes MMC to avoid high-density bias in clustering.
problem High-density bias in density-based clustering.
method Introduces mass distribution as a better foundation for clustering, proposing mass-maximization clustering (MMC).
result MMC avoids high-density bias and discovers clusters of arbitrary shapes, sizes, and densities.
New algorithms for fair data summarization in massive data models.
problem Fair k-center problem in massive data. method Streaming and distributed algorithms with provable guarantees.
result First distributed algorithm with constant approximation ratio.
Distributional Reinforcement Learning (RL) differs from traditional RL in that, rather than the expectation of total returns, it estimates distributions and has achieved state-of-the-art performance on Atari Games. The key challenge in practical distributional RL algorithms lies in how to parameterize estimated distrib…
A new distributed clustering framework using distributional kernel.
problem Clustering in distributed networks with arbitrary shapes, sizes, and densities.
method Distributed Clustering based on Distributional Kernel (KDC) using similarity of distributions.
result KDC guarantees equivalent clustering outcomes to centralized methods, reduces runtime, and discovers arbitrary clusters.
We study distributed optimization algorithms for minimizing the average of convex functions. The applications include empirical risk minimization problems in statistical machine learning where the datasets are large and have to be stored on different machines. We design a distributed stochastic variance reduced gradien…
Refined analysis of Mitra's algorithm for discrete mixtures.
problem Classifying general discrete mixture distribution models.
method Spectral clustering tailored to bipartite stochastic block models.
result Improved separation conditions for probability distributions.
As the size of modern data sets exceeds the disk and memory capacities of a single computer, machine learning practitioners have resorted to parallel and distributed computing. Given that optimization is one of the pillars of machine learning and predictive modeling, distributed optimization methods have recently garne…
New algorithm reduces individual regret and communication costs in cooperative bandits.
problem Optimal individual and group regret in cooperative multi-agent bandits.
method Integrates a new communication policy into a learning algorithm.
result Achieves optimal individual regret and constant communication costs.
This work develops secure distributed algorithms for machine learning to protect against data poisoning and network attacks.
problem Vulnerability of distributed machine learning algorithms to cyber threats.
method Game-theoretic framework to capture conflicting goals of a learner and an attacker, iterative distributed algorithm.
result Distributed SVM is prone to fail in different types of attacks, with impact depending on network structure and attack capabilities.
Transforms uniform learners to work under arbitrary distributions efficiently.
problem Learning under arbitrary distributions from uniform learners.
method Black-box transformation using decision tree decomposition.
result Efficient transformation with runtime scaling with distribution complexity.
Algorithm samples from Bingham distribution efficiently.
problem Sampling from the Bingham distribution on a sphere.
method Rejection sampling with polynomial approximation.
result Exact samples from Bingham distribution in polynomial time.
Study non-asymptotic Langevin Monte Carlo for Gibbs distributions.
problem Sampling from Gibbs distributions with dissipative potentials.
method Langevin-type algorithms based on Liptser--Shiryaev theory and Poincaré inequalities.
result Upper bound on 2-Wasserstein distance for accurate approximation.
Algorithm infers sampling distribution from i.i.d. samples without supervision.
problem Learning probability distributions from unlabeled data.
method Unsupervised tree boosting using additive tree ensembles and new distributional operations.
result Algorithm outperforms deep learning in multivariate density estimation.
New algorithm for sampling from distributions with thin tails.
problem Sampling from distributions with thin tails and theoretical guarantees.
method Proposes a Metropolized Algorithm With Optimization Step (MAO).
result Derives upper bounds on the mixing time of MAO.
New EM algorithm for mixtures of elliptical distributions handles missing data and outliers.
problem Missing data imputation for noisy and non-Gaussian data.
method Investigation of a new EM algorithm for mixtures of elliptical distributions.
result The proposed algorithm is robust to outliers and competitive with other methods.
New algorithm for RL using mean embeddings of return distributions.
problem Improving reinforcement learning algorithms for dynamic programming.
method Mean embeddings of return distributions, novel algorithms for RL.
result Asymptotic convergence and improved performance in deep RL.
New RL algorithm minimizes distributional learning error.
problem Improving distributional reinforcement learning for better error minimization.
method Proposes a new model-based algorithm with theoretical minimax optimality.
result Proves minimax optimality for approximating return distributions.
Proposes EDM algorithm to accelerate model training in distributed networks.
problem Hindered effectiveness of distributed stochastic optimization algorithms due to data heterogeneity and network sparsity.
method Introduces Exact-Diffusion with Momentum (EDM) algorithm, incorporating momentum techniques to mitigate bias and enhance convergence rate.
result EDM algorithm converges sub-linearly to the optimal solution, radius independent of data heterogeneity, for non-convex objective functions.
Two novel distributed VB algorithms improve Bayesian inference in sensor networks.
problem Efficient inference in Bayesian frameworks for sensor networks.
method Two novel distributed VB algorithms for general Bayesian inference, using stochastic natural gradient and ADMM.
result Distributed algorithms perform nearly as well as centralized ones, demonstrating excellent performance.
Proposes a general method to derive regret bounds for multi-armed bandit algorithms.
problem Deriving regret bounds for randomized multi-armed bandit algorithms.
method Checking sufficient conditions on sampling probabilities and distributions.
result Proves logarithmic regret bounds for various bandit algorithms and new models.
We present a unifying framework for designing and analysing distributional reinforcement learning (DRL) algorithms in terms of recursively estimating statistics of the return distribution. Our key insight is that DRL algorithms can be decomposed as the combination of some statistical estimator and a method for imputing…
In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and potentially adversarial behavior. In this paper, we develop distributed learning algorithm…
Paper introduces algorithms for private decision tree learning.
problem Private decision tree learning in distributed settings.
method Proposes DP-TopDown, NoisyCounts, and LocalRNM.
result First utility guarantees for private decision tree learning.
Two EM algorithms estimate prior distributions in mixture of linear regressions.
problem Estimating prior distributions in mixture of linear regressions.
method Two EM algorithms: one for continuous priors, one for discrete priors.
result Both algorithms accurately estimate prior distributions and the number of clusters.
In distributed ML applications, shared parameters are usually replicated among computing nodes to minimize network overhead. Therefore, proper consistency model must be carefully chosen to ensure algorithm's correctness and provide high throughput. Existing consistency models used in general-purpose databases and moder…
Paper shows fairness and domain adaptation can work together.
problem Algorithmic bias and distributional shifts in ML models.
method Leveraging fairness and distribution shifts, the paper shows how domain adaptation methods can mitigate bias.
result Enforcing individual fairness can improve out-of-distribution accuracy under covariate shift.
In reinforcement learning an agent interacts with the environment by taking actions and observing the next state and reward. When sampled probabilistically, these state transitions, rewards, and actions can all induce randomness in the observed long-term return. Traditionally, reinforcement learning algorithms average …
LocalKMeans parallelizes Lloyd's algorithm for distributed data.
problem Efficiently clustering data across multiple machines.
method Parallel local iterations with synchronization every L steps.
result Higher required signal-to-noise ratio due to local steps.
MLI is an Application Programming Interface designed to address the challenges of building Machine Learn- ing algorithms in a distributed setting based on data-centric computing. Its primary goal is to simplify the development of high-performance, scalable, distributed algorithms. Our initial results show that, relativ…
We provide a differentially private algorithm for hypothesis selection. Given samples from an unknown probability distribution P and a set of m probability distributions H, the goal is to output, in a ε-differentially private manner, a distribution from H whose total variation di…
Regularizes ML algorithms for robust multivariate analysis against distribution shifts.
problem Ensuring robustness of multivariate analysis algorithms against distribution shifts.
method Integrates a causal regularisation term into the loss function of multivariate analysis algorithms.
result Demonstrates improved out-of-distribution generalisation with reduced-rank regression and partial least squares.
New algorithm learns changing discrete distributions with minimal drift error.
problem Learning discrete distributions that change over time with limited past samples.
method Adaptive algorithm using data-dependent bounds to balance statistical and drift errors.
result Tighter statistical error bounds for drifting distributions with or without finite support.
Unsupervised learning representations generalize better than supervised learning under distribution shifts.
problem Robustness of unsupervised representations to distribution shift.
method Extensive evaluation on synthetic and realistic datasets, including controllable domain generalization datasets.
result Unsupervised representations learned from SSL and AE generalize better than supervised learning under various distribution shifts.
In this article, we focus on distributed Apriori-based frequent itemsets mining. We present a new distributed approach which takes into account inherent characteristics of this algorithm. We study the distribution aspect of this algorithm and give a comparison of the proposed approach with a classical Apriori-like dist…
Paper designs a bandit algorithm without reward distribution info.
problem Designing bandit algorithms without reward distribution info.
method Alternates between greedy rule and forced exploration.
result Achieves substantial regret upper bounds.
We consider distributed on-device learning with limited communication and security requirements. We propose a new robust distributed optimization algorithm with efficient communication and attack tolerance. The proposed algorithm has provable convergence and robustness under non-IID settings. Empirical results show tha…
We investigate an existing distributed algorithm for learning sparse signals or data over networks. The algorithm is iterative and exchanges intermediate estimates of a sparse signal over a network. This learning strategy using exchange of intermediate estimates over the network requires a limited communication overhea…
No free lunch theorems show all algorithms perform equally under uniform distribution.
problem Analyzing scenarios involving non-uniform distributions and comparing algorithms.
method No Free Lunch theorems applied to analyze and compare algorithms without distribution assumptions.
result Anti-cross-validation performs as well as cross-validation under non-uniform distributions.
Unified analysis of efficient local training methods for distributed variational inequalities.
problem Efficient distributed/federated learning for variational inequality problems.
method Unified convergence analysis of communication-efficient local training methods.
result First local gradient descent-accent algorithms with improved communication complexity.
Paper introduces a new distributional successor measure for reinforcement learning.
problem Learning the distributional consequences of behavior in reinforcement learning.
method Formulates distributional successor measure as a distribution over distributions, proposes algorithm to learn it from data.
result Demonstrates zero-shot risk-sensitive policy evaluation.
We give an algorithm for completing an order-m symmetric low-rank tensor from its multilinear entries in time roughly proportional to the number of tensor entries. We apply our tensor completion algorithm to the problem of learning mixtures of product distributions over the hypercube, obtaining new algorithmic result…