Sequential 1-bit Mean Estimation with Near-Optimal Sample Complexity

In this paper, we study the problem of distributed mean estimation with 1-bit communication constraints. We propose a mean estimator that is based on (randomized and sequentially-chosen) interval queries, whose 1-bit outcome indicates whether the given sample lies in the specified interval. Our estimator is $(\epsilon, \delta)$-PAC for all distributions with bounded mean ($-\lambda \le \mathbb{E}(X) \le \lambda $) and variance ($\mathrm{Var}(X) \le \sigma^2$) for some known parameters $\lambda$ and $\sigma$. We derive a sample complexity bound $\widetilde{O}\big( \frac{\sigma^2}{\epsilon^2}\log\frac{1}{\delta} + \log\frac{\lambda}{\sigma}\big)$, which matches the minimax lower bound for the unquantized setting up to logarithmic factors and the additional $\log\frac{\lambda}{\sigma}$ term that we show to be unavoidable. We also establish an adaptivity gap for interval-query based estimators: the best non-adaptive mean estimator is considerably worse than our adaptive mean estimator for large $\frac{\lambda}{\sigma}$. Finally, we give tightened sample complexity bounds for distributions with stronger tail decay, and present additional variants that (i) handle an unknown sampling budget (ii) adapt to the unknown true variance given (possibly loose) upper and lower bounds on the variance, and (iii) use only two stages of adaptivity at the expense of more complicated (non-interval) queries.

Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards

We study stochastic linear bandits with heavy-tailed rewards, where the rewards have a finite $(1+\epsilon)$-absolute central moment bounded by $\upsilon$ for some $\epsilon \in (0,1]$. We improve both upper and lower bounds on the minimax regret compared to prior work. When $\upsilon = \mathcal{O}(1)$, the best prior known regret upper bound is $\tilde{\mathcal{O}}(d T^{\frac{1}{1+\epsilon}})$. While a lower with the same scaling has been given, it relies on a construction using $\upsilon = \mathcal{O}(d)$, and adapting the construction to the bounded-moment regime with $\upsilon = \mathcal{O}(1)$ yields only a $\Omega(d^{\frac{\epsilon}{1+\epsilon}} T^{\frac{1}{1+\epsilon}})$ lower bound. This matches the known rate for multi-armed bandits and is generally loose for linear bandits, in particular being $\sqrt{d}$ below the optimal rate in the finite-variance case ($\epsilon = 1$). We propose a new elimination-based algorithm guided by experimental design, which achieves regret $\tilde{\mathcal{O}}(d^{\frac{1+3\epsilon}{2(1+\epsilon)}} T^{\frac{1}{1+\epsilon}})$, thus improving the dependence on $d$ for all $\epsilon \in (0,1)$ and recovering a known optimal result for $\epsilon = 1$. We also establish a lower bound of $\Omega(d^{\frac{2\epsilon}{1+\epsilon}} T^{\frac{1}{1+\epsilon}})$, which strictly improves upon the multi-armed bandit rate and highlights the hardness of heavy-tailed linear bandit problems. For finite action sets, we derive similarly improved upper and lower bounds for regret. Finally, we provide action set dependent regret upper bounds showing that for some geometries, such as $l_p$-norm balls for $p \le 1 + \epsilon$, we can further reduce the dependence on $d$, and we can handle infinite-dimensional settings via the kernel trick, in particular establishing new regret bounds for the Mat\'ern kernel that are the first to be sublinear for all $\epsilon \in (0, 1]$.

Statistical Mean Estimation with Coded Relayed Observations

We consider a problem of statistical mean estimation in which the samples are not observed directly, but are instead observed by a relay (``teacher'') that transmits information through a memoryless channel to the decoder (``student''), who then produces the final estimate. We consider the minimax estimation error in the large deviations regime, and establish achievable error exponents that are tight in broad regimes of the estimation accuracy and channel quality. In contrast, two natural baseline methods are shown to yield strictly suboptimal error exponents. We initially focus on Bernoulli sources and binary symmetric channels, and then generalize to sub-Gaussian and heavy-tailed settings along with arbitrary discrete memoryless channels.

Quantile Multi-Armed Bandits with 1-bit Feedback

In this paper, we study a variant of best-arm identification involving elements of risk sensitivity and communication constraints. Specifically, the goal of the learner is to identify the arm with the highest quantile reward, while the communication from an agent (who observes rewards) and the learner (who chooses actions) is restricted to only one bit of feedback per arm pull. We propose an algorithm that utilizes noisy binary search as a subroutine, allowing the learner to estimate quantile rewards through 1-bit feedback. We derive an instance-dependent upper bound on the sample complexity of our algorithm and provide an algorithm-independent lower bound for specific instances, with the two matching to within logarithmic factors under mild conditions, or even to within constant factors in certain low error probability scaling regimes. The lower bound is applicable even in the absence of communication constraints, and thus we conclude that restricting to 1-bit feedback has a minimal impact on the scaling of the sample complexity.

Lower Bounds for Time-Varying Kernelized Bandits

The optimization of black-box functions with noisy observations is a fundamental problem with widespread applications, and has been widely studied under the assumption that the function lies in a reproducing kernel Hilbert space (RKHS). This problem has been studied extensively in the stationary setting, and near-optimal regret bounds are known via developments in both upper and lower bounds. In this paper, we consider non-stationary scenarios, which are crucial for certain applications but are currently less well-understood. Specifically, we provide the first algorithm-independent lower bounds, where the time variations are subject satisfying a total variation budget according to some function norm. Under $\ell_{\infty}$-norm variations, our bounds are found to be close to the state-of-the-art upper bound (Hong \emph{et al.}, 2023). Under RKHS norm variations, the upper and lower bounds are still reasonably close but with more of a gap, raising the interesting open question of whether non-minor improvements in the upper bound are possible.

A General Framework for Clustering and Distribution Matching with Bandit Feedback

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a $K$-armed bandit model where some subset of $K$ arms is partitioned into $M$ groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value $\delta$. Several existing problems fall under our general framework, including finding $M$ pairs of arms, odd arm identification, and $M$-ary clustering of $K$ arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding $\delta$. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank--Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as $\delta$ vanishes.

Robust Instance Optimal Phase-Only Compressed Sensing

Phase-only compressed sensing (PO-CS) is concerned with the recovery of structured signals from the phases of complex measurements. Recent results show that structured signals in the standard sphere $\mathbb{S}^{n-1}$ can be exactly recovered from complex Gaussian phases, by recasting PO-CS as linear compressed sensing and then applying existing solvers such as basis pursuit. Known guarantees are either non-uniform or do not tolerate model error. We show that this linearization approach is more powerful than the prior results indicate. First, it achieves uniform instance optimality: Under complex Gaussian matrix with a near-optimal number of rows, this approach uniformly recovers all signals in $\mathbb{S}^{n-1}$ with errors proportional to the model errors of the signals. Specifically, for sparse recovery there exists an efficient estimator $\mathbf{x}^\sharp$ and some universal constant $C$ such that $\|\mathbf{x}^\sharp-\mathbf{x}\|_2\le \frac{C\sigma_s(\mathbf{x})_1}{\sqrt{s}}~(\forall\mathbf{x}\in\mathbb{S}^{n-1})$, where $\sigma_s(\mathbf{x})_1=\min_{\mathbf{u}\in\Sigma^n_s}\|\mathbf{u}-\mathbf{x}\|_1$ is the model error under $\ell_1$-norm. Second, the instance optimality is robust to small dense disturbances and sparse corruptions that arise before or after capturing the phases. As an extension, we also propose to recast sparsely corrupted PO-CS as a linear corrupted sensing problem and show that this achieves perfect reconstruction of the signals. Our results resemble the instance optimal guarantees in linear compressed sensing and, to our knowledge, are the first results of this kind for a non-linear sensing scenario.

Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization

Bi-level optimization (BO) has become a fundamental mathematical framework for addressing hierarchical machine learning problems. As deep learning models continue to grow in size, the demand for scalable bi-level optimization solutions has become increasingly critical. Traditional gradient-based bi-level optimization algorithms, due to their inherent characteristics, are ill-suited to meet the demands of large-scale applications. In this paper, we introduce $\textbf{F}$orward $\textbf{G}$radient $\textbf{U}$nrolling with $\textbf{F}$orward $\textbf{F}$radient, abbreviated as $(\textbf{FG})^2\textbf{U}$, which achieves an unbiased stochastic approximation of the meta gradient for bi-level optimization. $(\text{FG})^2\text{U}$ circumvents the memory and approximation issues associated with classical bi-level optimization approaches, and delivers significantly more accurate gradient estimates than existing large-scale bi-level optimization approaches. Additionally, $(\text{FG})^2\text{U}$ is inherently designed to support parallel computing, enabling it to effectively leverage large-scale distributed computing systems to achieve significant computational efficiency. In practice, $(\text{FG})^2\text{U}$ and other methods can be strategically placed at different stages of the training process to achieve a more cost-effective two-phase paradigm. Further, $(\text{FG})^2\text{U}$ is easy to implement within popular deep learning frameworks, and can be conveniently adapted to address more challenging zeroth-order bi-level optimization scenarios. We provide a thorough convergence analysis and a comprehensive practical discussion for $(\text{FG})^2\text{U}$, complemented by extensive empirical evaluations, showcasing its superior performance in diverse large-scale bi-level optimization tasks.

No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraints

We consider the problem of sequentially maximizing an unknown function $f$ over a set of actions of the form $(s,\mathbf{x})$, where the selected actions must satisfy a safety constraint with respect to an unknown safety function $g$. We model $f$ and $g$ as lying in a reproducing kernel Hilbert space (RKHS), which facilitates the use of Gaussian process methods. While existing works for this setting have provided algorithms that are guaranteed to identify a near-optimal safe action, the problem of attaining low cumulative regret has remained largely unexplored, with a key challenge being that expanding the safe region can incur high regret. To address this challenge, we show that if $g$ is monotone with respect to just the single variable $s$ (with no such constraint on $f$), sublinear regret becomes achievable with our proposed algorithm. In addition, we show that a modified version of our algorithm is able to attain sublinear regret (for suitably defined notions of regret) for the task of finding a near-optimal $s$ corresponding to every $\mathbf{x}$, as opposed to only finding the global safe optimum. Our findings are supported with empirical evaluations on various objective and safety functions.

Kernelized Normalizing Constant Estimation: Bridging Bayesian Quadrature and Bayesian Optimization

In this paper, we study the problem of estimating the normalizing constant $\int e^{-\lambda f(x)}dx$ through queries to the black-box function $f$, where $f$ belongs to a reproducing kernel Hilbert space (RKHS), and $\lambda$ is a problem parameter. We show that to estimate the normalizing constant within a small relative error, the level of difficulty depends on the value of $\lambda$: When $\lambda$ approaches zero, the problem is similar to Bayesian quadrature (BQ), while when $\lambda$ approaches infinity, the problem is similar to Bayesian optimization (BO). More generally, the problem varies between BQ and BO. We find that this pattern holds true even when the function evaluations are noisy, bringing new aspects to this topic. Our findings are supported by both algorithm-independent lower bounds and algorithmic upper bounds, as well as simulation studies conducted on a variety of benchmark functions.