New algorithm achieves linear speedup in non-i.i.d. federated bilevel learning.
problem Linear speedup in convergence for non-i.i.d. datasets in federated bilevel optimization.
method Proposes FedMBO with a novel client sampling scheme for non-i.i.d. datasets.
result Achieves a convergence rate of O(1/√(nK) + 1/K + √n/K³/²).
Study improves KRR for non-i.i.d. data, with applications in denoising.
problem Kernel regression in structured non-i.i.d. settings.
method Developed a blockwise decomposition method for dependent data, deriving excess risk bounds.
result Established generalization guarantees for KRR in non-i.i.d. settings.
We study the task of learning from non-i.i.d. data. In particular, we aim at learning predictors that minimize the conditional risk for a stochastic process, i.e. the expected loss of the predictor on the next point conditioned on the set of training samples observed so far. For non-i.i.d. data, the training set contai…
A method to robustly federate learning with non-i.i.d. data and Byzantine workers.
problem Byzantine workers sending malicious messages in federated learning with non-i.i.d. data.
method Resampling strategy to reduce inner and outer variation, stochastic average gradient, robust geometric median aggregation.
result The method reaches a neighborhood of the optimal solution at a linear convergence rate and learning error depends on the number of Byzantine workers.
Temporal Difference Learning analysis under non-i.i.d. data and nonlinear approximation.
problem Finite-sample behavior of TD(0) under non-i.i.d. data and nonlinear approximation.
method High-probability, finite-sample analysis of vanilla TD(0) on polynomially mixing Markov data, assuming Holder continuity and bounded generalized gradients.
result Bounds on the convergence rate of TD(0) with high probability, matching known i.i.d. rates and holding even with nonstationary initialization.
Study improves off-policy evaluation from non-i.i.d. bandit samples.
problem Improving off-policy evaluation from non-independent bandit samples.
method Constructing an estimator from a standardized martingale difference sequence.
result Proposed estimator performs better than existing methods.
This work develops a non-parametric test for relational independence in non-i.i.d. data.
problem Testing independence in relational systems where data samples are not i.i.d.
method Kernel mean embedding for relational variables, consistent non-parametric scalable kernel test.
result Empirically validated effectiveness compared to state-of-the-art tests.
The paper improves Q-learning by incorporating pessimism for better sample efficiency.
problem Improving sample efficiency in asynchronous Q-learning with non-i.i.d. data.
method Developed an algorithmic framework that incorporates the principle of pessimism into asynchronous Q-learning, penalizing infrequently-visited state-action pairs based on suitable lower confidence bounds (LCBs).
result Achieved near-optimal sample complexity, providing theoretical support for the use of pessimism in non-i.i.d. data.
The paper improves conformal prediction by analyzing the beta law of conditional coverage.
problem Improving finite-sample marginal coverage guarantees for non-i.i.d. data.
method The method uses Wasserstein distances to quantify deviations from the beta law of conditional coverage.
result The framework provides direct bounds on marginal coverage gaps and bad-calibration probabilities.
New theory explains consistency of kernel methods with non-i.i.d. data.
problem Consistency of kernel methods under non-i.i.d. data.
method Empirical weak convergence (EWC) as a general assumption.
result Established consistency of SVMs, kernel mean embeddings, and CKMEs with EWC data.
Paper analyzes CRL generalization under non-i.i.d. settings, providing bounds for practical data reuse.
problem Limited theoretical understanding of CRL generalization under non-i.i.d. data conditions.
method Inspired by U-statistics, derives generalization bounds for CRL under non-i.i.d. settings.
result Required number of samples scales logarithmically with class covering number.
SARSA is an on-policy algorithm to learn a Markov decision process policy in reinforcement learning. We investigate the SARSA algorithm with linear function approximation under the non-i.i.d.\ data, where a single sample trajectory is available. With a Lipschitz continuous policy improvement operator that is smooth eno…
A universal framework for constructing confidence sets using sequential likelihood mixing.
problem Constructing reliable confidence sets for realizable likelihood functions.
method Sequential likelihood mixing, integrating Bayesian inference and regret inequalities.
result Establishes fundamental connections and provable coverage guarantees for various inference techniques.
This paper focuses on learning rate analysis of distributed kernel ridge regression for strong mixing sequences. Using a recently developed integral operator approach and a classical covariance inequality for Banach-valued strong mixing sequences, we succeed in deriving optimal learning rate for distributed kernel ridg…
New method improves representation learning from non-i.i.d. and non-isotropic data.
problem Improving representation learning from non-i.i.d. and non-isotropic data.
method Introducing a new adaptation of alternating minimization-descent scheme to reduce noise scaling.
result Established linear convergence to optimal representation with noise scaling down with total source data size.
MaxCOSD algorithm tackles non-i.i.d. demands and stateful dynamics in online inventory control.
problem Managing inventory with non-i.i.d. demands and stateful dynamics.
method MaxCOSD, an online algorithm with provable guarantees for non-degeneracy assumptions.
result MaxCOSD achieves optimal performance for non-i.i.d. demands and stateful dynamics.
New bandit algorithm for non-i.i.d. noise, improving standard rates.
problem Linear stochastic bandit with non-i.i.d. observation noise.
method Developed new confidence sequences and an algorithm based on optimism in uncertainty.
result Regret bounds for the new algorithm, showing recovery of standard rates up to a factor of the mixing time.
Paper extends SMM to weakly convex and multi-convex surrogates for non-convex optimization.
problem Non-convex optimization with weakly convex or multi-convex surrogates.
method Stochastic majorization-minimization with proximal regularization or block-minimization.
result Convergence rates for empirical and expected losses under non-i.i.d. data.
Paper analyzes Nyström regularization for time series forecasting with sequential sub-sampling.
problem Learning rate analysis of Nyström regularization for τ-mixing time series. method Banach-valued Bernstein inequality and integral operator approach for τ-mixing sequences. result Almost optimal learning rates for Nyström regularization with sequential sub-sampling.
New findings show many popular bandit algorithms are unstable, contradicting minimax optimality.
problem Challenges in statistical inference from bandit algorithms due to adaptive, non-i.i.d. nature.
method Analysis of stability properties of optimism-based bandit algorithms.
result Widely used minimax-optimal UCB-style algorithms are unstable.
Improved Nyström approximation for kernel quadrature with theoretical guarantees.
problem Efficiently approximating positive definite kernels for large datasets.
method Refined sampling and subspace selection in Nyström approximation.
result Novel theoretical guarantees for non-i.i.d. landmark points in kernel quadrature.
FedBE aggregates local models into a robust global model via Bayesian inference.
problem Challenges in aggregating non-i.i.d. local models into a global model in federated learning.
method FedBE uses Bayesian inference to sample and combine higher-quality global models from local models.
result FedBE leads to more robust aggregation of local models into a global model, especially when data is non-i.i.d.
We present a generative model that is defined on finite sets of exchangeable, potentially high dimensional, data. As the architecture is an extension of RealNVPs, it inherits all its favorable properties, such as being invertible and allowing for exact log-likelihood evaluation. We show that this architecture is able t…
New federated learning framework reduces model complexity and improves performance.
problem Slow convergence in traditional federated learning due to non-i.i.d. data.
method Clients train personalized local models, server trains shared model, addressing heterogeneity.
result Substantial performance gains over baselines, robust to non-i.i.d. data.
This paper precisely estimates transformer derivatives for explicit learning guarantees.
problem Computing fully-explicit generalization bounds for transformers with precise higher-order derivative estimates.
method Analyzes and estimates all higher-order derivatives of transformers with multiple attention heads and layer normalization.
result Obtains explicit pathwise generalization bounds for transformers learning from non-i.i.d. samples.
Improved statistical inference for adaptive Thompson Sampling.
problem Statistical inference challenges in Thompson Sampling.
method Inflating posterior variance in Thompson Sampling.
result Asymptotically normal estimates of arm means with logarithmic regret increase.
New algorithms for regression with adversarial responses on various metric spaces.
problem Regression with adversarial responses under non-i.i.d. sequences.
method Proves universal consistency for a wide range of non-stationary processes.
result Achieves universal consistency for a broader class of sequences than stationary processes.
The paper proposes a method to monitor deep learning predictions for retraining, reducing costs.
problem Reducing computational costs in deep learning by detecting when predictions are no longer valid.
method Sequential monitoring of network predictions based on projected second moments monitoring.
result The proposed method can drastically reduce computational costs in deep learning.
FedIV uses federated GMM for IV analysis in non-i.i.d. data.
problem Efficient IV analysis in non-i.i.d. federated data.
method Federated GMM via FedGDA algorithm.
result Federated solution consistently estimates local moment conditions.
Paper optimizes FL communication efficiency with stochastic optimization.
problem Intermittent connectivity and non-i.i.d. data in FL.
method Convergence analysis of non-convex loss functions, stochastic optimization for client selection and power allocation.
result Significant reduction in communication time compared to random participation.
We present an new sequential Monte Carlo sampler for coalescent based Bayesian hierarchical clustering. Our model is appropriate for modeling non-i.i.d. data and offers a substantial reduction of computational cost when compared to the original sampler without resorting to approximations. We also propose a quadratic co…
We address the problem of defining a network graph on a large collection of classes. Each class is comprised of a collection of data points, sampled in a non i.i.d. way, from some unknown underlying distribution. The application we consider in this paper is a large scale high dimensional survey of people living in the …
Unified analysis of Federated Averaging and Nesterov FedAvg for linear speedup.
problem Understanding convergence of FL algorithms under non-i.i.d. data and partial participation.
method Systematic study of convergence guarantees for FedAvg and Nesterov FedAvg under different conditions.
result Unified analysis of linear speedup for FedAvg and Nesterov FedAvg in various settings.
We present a novel statistical inference framework for convex empirical risk minimization, using approximate stochastic Newton steps. The proposed algorithm is based on the notion of finite differences and allows the approximation of a Hessian-vector product from first-order information. In theory, our method efficient…
We propose a nonparametric statistical test for goodness-of-fit: given a set of samples, the test determines how likely it is that these were generated from a target density function. The measure of goodness-of-fit is a divergence constructed via Stein's method using functions from a Reproducing Kernel Hilbert Space. O…
Unified framework for representation and causal structure learning using exchangeable data.
problem Identifying latent representations or causal structures in non-i.i.d. data.
method Identifiable Exchangeable Mechanisms (IEM) framework for representation and structure learning.
result New insights and identifiability results for causal structure and representation learning.
This paper tackles online strategic decision making with asymmetry and knowledge transportability.
problem Strategic decision making with information asymmetry and knowledge transportability challenges.
method Developed a sample-efficient algorithm for online learning under these conditions.
result Proved sample complexity of O(1/ε2) for learning an ε-optimal policy. Novel risk bound for structured prediction tackles non-i.i.d. data.
problem Structured prediction challenges due to non-factorizable target objects.
method PAC-Bayesian risk bound with explicit structure distillation.
result Generalization rate scales with data size and structure.
This work analyzes actor-critic methods for faster convergence.
problem Finite-time analysis and sample complexity of two-time-scale actor-critic methods.
method Non-asymptotic analysis under non-i.i.d. setting, proving convergence to first-order stationary point.
result Actor-critic method finds a first-order stationary point with ildeO(ε−2.5) sample complexity. Gradient-based temporal difference (GTD) algorithms are widely used in off-policy learning scenarios. Among them, the two time-scale TD with gradient correction (TDC) algorithm has been shown to have superior performance. In contrast to previous studies that characterized the non-asymptotic convergence rate of TDC only…
The paper improves Bayesian optimization by calibrating uncertainty estimates.
problem Improper uncertainty estimates in Bayesian optimization when data is non-stationary.
method Proposes online learning algorithms to maintain calibration on non-i.i.d. data and integrates them into Bayesian optimization.
result Calibrated Bayesian optimization converges to better optima in fewer steps.
A crucial assumption in most statistical learning theory is that samples are independently and identically distributed (i.i.d.). However, for many real applications, the i.i.d. assumption does not hold. We consider learning problems in which examples are dependent and their dependency relation is characterized by a gra…
New Gaussian min-max theorem extends classical results to non-i.i.d. Gaussian matrices.
problem Extending classical Gaussian min-max theorems to non-i.i.d. Gaussian matrices.
method Identifying a new pair of Gaussian processes that satisfy comparison inequalities.
result New Gaussian min-max and convex Gaussian min-max theorems with applications in multi-source Gaussian regression and binary classification.
We introduce and study the problem of Online Continual Compression, where one attempts to simultaneously learn to compress and store a representative dataset from a non i.i.d data stream, while only observing each sample once. A naive application of auto-encoders in this setting encounters a major challenge: representa…
FedNAS automates federated learning by searching for better architectures.
problem Non-I.I.D. data makes predefined model architectures suboptimal.
method Federated Neural Architecture Search (FedNAS) for collaborative architecture optimization.
result FedNAS searches for better architectures that outperform predefined models.
Differential privacy formalises privacy-preserving mechanisms that provide access to a database. We pose the question of whether Bayesian inference itself can be used directly to provide private access to data, with no modification. The answer is affirmative: under certain conditions on the prior, sampling from the pos…
Robotic vision is a field where continual learning can play a significant role. An embodied agent operating in a complex environment subject to frequent and unpredictable changes is required to learn and adapt continuously. In the context of object recognition, for example, a robot should be able to learn (without forg…
We present a distributionally robust formulation of a stochastic optimization problem for non-i.i.d vector autoregressive data. We use the Wasserstein distance to define robustness in the space of distributions and we show, using duality theory, that the problem is equivalent to a finite convex-concave saddle point pro…