BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Constantine Caramanis

Constantine Caramanis contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningInformation Theorymath.ITmath.OCSocial and Information NetworksApplicationsArtificial IntelligenceCryptography and Securitycs.CYData Structures and Algorithmsmath.STphysics.soc-phStatistics Theory

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
15works
0followers
13topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

15 published item(s)

preprint2026arXiv

MaxSketch: Robust Distinct Counting in Streams via Random Projections

Estimating the number of distinct elements in a data stream is well understood when repeated elements are identical. In modern settings, however, observations are high-dimensional and noisy, so repeated instances of the same object are only approximately similar -- for example, different images of the same individual may vary significantly at the pixel level. Classical sketches such as HyperLogLog rely on consistent hash values for identical elements and break down in this regime. Recent work on robust distinct counting in general metric spaces achieves $\widetildeΘ(\sqrt{n})$ memory, which is tight in the worst case. We show that substantially improved memory guarantees are possible under geometric structure common in learned representations. We introduce MaxSketch, a simple max-linear sketch built from random Gaussian projections, and prove that it succeeds in estimating the number of distinct latent objects. Concretely, we show that under this assumption $m = \widetilde{O} (\log n / \varepsilon^2)$ random projections (and hence $\widetilde{O} (\log n/\varepsilon^2)$ memory) suffice to recover the true distinct count within a $(1+\varepsilon)$ factor. Experiments on image streams confirm that MaxSketch accurately estimates distinct counts and generalizes beyond the training regime. Our results bridge classical streaming algorithms and modern representation learning, showing how geometric structure can fundamentally reduce the complexity of distinct counting.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms

Motivated by online recommendation systems, we propose the problem of finding the optimal policy in multitask contextual bandits when a small fraction $α< 1/2$ of tasks (users) are arbitrary and adversarial. The remaining fraction of good users share the same instance of contextual bandits with $S$ contexts and $A$ actions (items). Naturally, whether a user is good or adversarial is not known in advance. The goal is to robustly learn the policy that maximizes rewards for good users with as few user interactions as possible. Without adversarial users, established results in collaborative filtering show that $O(1/ε^2)$ per-user interactions suffice to learn a good policy, precisely because information can be shared across users. This parallelization gain is fundamentally altered by the presence of adversarial users: unless there are super-polynomial number of users, we show a lower bound of $\tildeΩ(\min(S,A) \cdot α^2 / ε^2)$ {\it per-user} interactions to learn an $ε$-optimal policy for the good users. We then show we can achieve an $\tilde{O}(\min(S,A)\cdot α/ε^2)$ upper-bound, by employing efficient robust mean estimators for both uni-variate and high-dimensional random variables. We also show that this can be improved depending on the distributions of contexts.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Reinforcement Learning in Reward-Mixing MDPs

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP). There, a reward function is drawn from one of multiple possible reward models at the beginning of every episode, but the identity of the chosen reward model is not revealed to the agent. Hence, the latent state space, for which the dynamics are Markovian, is not given to the agent. We study the problem of learning a near optimal policy for two reward-mixing MDPs. Unlike existing approaches that rely on strong assumptions on the dynamics, we make no assumptions and study the problem in full generality. Indeed, with no further assumptions, even for two switching reward-models, the problem requires several new ideas beyond existing algorithmic and analysis techniques for efficient exploration. We provide the first polynomial-time algorithm that finds an $ε$-optimal policy after exploring $\tilde{O}(poly(H,ε^{-1}) \cdot S^2 A^2)$ episodes, where $H$ is time-horizon and $S, A$ are the number of states and actions respectively. This is the first efficient algorithm that does not require any assumptions in partially observed environments where the observation space is smaller than the latent state space.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance

We study convergence rates of AdaGrad-Norm as an exemplar of adaptive stochastic gradient methods (SGD), where the step sizes change based on observed stochastic gradients, for minimizing non-convex, smooth objectives. Despite their popularity, the analysis of adaptive SGD lags behind that of non adaptive methods in this setting. Specifically, all prior works rely on some subset of the following assumptions: (i) uniformly-bounded gradient norms, (ii) uniformly-bounded stochastic gradient variance (or even noise support), (iii) conditional independence between the step size and stochastic gradient. In this work, we show that AdaGrad-Norm exhibits an order optimal convergence rate of $\mathcal{O}\left(\frac{\mathrm{poly}\log(T)}{\sqrt{T}}\right)$ after $T$ iterations under the same assumptions as optimally-tuned non adaptive SGD (unbounded gradient norms and affine noise variance scaling), and crucially, without needing any tuning parameters. We thus establish that adaptive gradient methods exhibit order-optimal convergence in much broader regimes than previously understood.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

On the computational and statistical complexity of over-parameterized matrix sensing

We consider solving the low rank matrix sensing problem with Factorized Gradient Descend (FGD) method when the true rank is unknown and over-specified, which we refer to as over-parameterized matrix sensing. If the ground truth signal $\mathbf{X}^* \in \mathbb{R}^{d*d}$ is of rank $r$, but we try to recover it using $\mathbf{F} \mathbf{F}^\top$ where $\mathbf{F} \in \mathbb{R}^{d*k}$ and $k>r$, the existing statistical analysis falls short, due to a flat local curvature of the loss function around the global maxima. By decomposing the factorized matrix $\mathbf{F}$ into separate column spaces to capture the effect of extra ranks, we show that $\|\mathbf{F}_t \mathbf{F}_t - \mathbf{X}^*\|_{F}^2$ converges to a statistical error of $\tilde{\mathcal{O}} ({k d σ^2/n})$ after $\tilde{\mathcal{O}}(\frac{σ_{r}}σ\sqrt{\frac{n}{d}})$ number of iterations where $\mathbf{F}_t$ is the output of FGD after $t$ iterations, $σ^2$ is the variance of the observation noise, $σ_{r}$ is the $r$-th largest eigenvalue of $\mathbf{X}^*$, and $n$ is the number of sample. Our results, therefore, offer a comprehensive picture of the statistical and computational complexity of FGD for the over-parameterized matrix sensing problem.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

On the Minimax Optimality of the EM Algorithm for Learning Two-Component Mixed Linear Regression

We study the convergence rates of the EM algorithm for learning two-component mixed linear regression under all regimes of signal-to-noise ratio (SNR). We resolve a long-standing question that many recent results have attempted to tackle: we completely characterize the convergence behavior of EM, and show that the EM algorithm achieves minimax optimal sample complexity under all SNR regimes. In particular, when the SNR is sufficiently large, the EM updates converge to the true parameter $θ^{*}$ at the standard parametric convergence rate $\mathcal{O}((d/n)^{1/2})$ after $\mathcal{O}(\log(n/d))$ iterations. In the regime where the SNR is above $\mathcal{O}((d/n)^{1/4})$ and below some constant, the EM iterates converge to a $\mathcal{O}({\rm SNR}^{-1} (d/n)^{1/2})$ neighborhood of the true parameter, when the number of iterations is of the order $\mathcal{O}({\rm SNR}^{-2} \log(n/d))$. In the low SNR regime where the SNR is below $\mathcal{O}((d/n)^{1/4})$, we show that EM converges to a $\mathcal{O}((d/n)^{1/4})$ neighborhood of the true parameters, after $\mathcal{O}((n/d)^{1/2})$ iterations. Notably, these results are achieved under mild conditions of either random initialization or an efficiently computable local initialization. By providing tight convergence guarantees of the EM algorithm in middle-to-low SNR regimes, we fill the remaining gap in the literature, and significantly, reveal that in low SNR, EM changes rate, matching the $n^{-1/4}$ rate of the MLE, a behavior that previous work had been unable to show.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Quarantines as a Targeted Immunization Strategy

In the context of the recent COVID-19 outbreak, quarantine has been used to &#34;flatten the curve&#34; and slow the spread of the disease. In this paper, we show that this is not the only benefit of quarantine for the mitigation of an SIR epidemic spreading on a graph. Indeed, human contact networks exhibit a powerlaw structure, which means immunizing nodes at random is extremely ineffective at slowing the epidemic, while immunizing high-degree nodes can efficiently guarantee herd immunity. We theoretically prove that if quarantines are declared at the right moment, high-degree nodes are disproportionately in the Removed state, which is a form of targeted immunization. Even if quarantines are declared too early, subsequent waves of infection spread slower than the first waves. This leads us to propose an opening and closing strategy aiming at immunizing the graph while infecting the minimum number of individuals, guaranteeing the population is now robust to future infections. To the best of our knowledge, this is the only strategy that guarantees herd immunity without requiring vaccines. We extensively verify our results on simulated and real-life networks.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Recurrent Submodular Welfare and Matroid Blocking Bandits

A recent line of research focuses on the study of the stochastic multi-armed bandits problem (MAB), in the case where temporal correlations of specific structure are imposed between the player&#39;s actions and the reward distributions of the arms (Kleinberg and Immorlica [FOCS18], Basu et al. [NeurIPS19]). As opposed to the standard MAB setting, where the optimal solution in hindsight can be trivially characterized, these correlations lead to (sub-)optimal solutions that exhibit interesting dynamical patterns -- a phenomenon that yields new challenges both from an algorithmic as well as a learning perspective. In this work, we extend the above direction to a combinatorial bandit setting and study a variant of stochastic MAB, where arms are subject to matroid constraints and each arm becomes unavailable (blocked) for a fixed number of rounds after each play. A natural common generalization of the state-of-the-art for blocking bandits, and that for matroid bandits, yields a $(1-\frac{1}{e})$-approximation for partition matroids, yet it only guarantees a $\frac{1}{2}$-approximation for general matroids. In this paper we develop new algorithmic ideas that allow us to obtain a polynomial-time $(1 - \frac{1}{e})$-approximation algorithm (asymptotically and in expectation) for any matroid, and thus to control the $(1-\frac{1}{e})$-approximate regret. A key ingredient is the technique of correlated (interleaved) scheduling. Along the way, we discover an interesting connection to a variant of Submodular Welfare Maximization, for which we provide (asymptotically) matching upper and lower approximability bounds.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

RL for Latent MDPs: Regret Guarantees and a Lower Bound

In this work, we consider the regret minimization problem for reinforcement learning in latent Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of $M$ possible MDPs at the beginning of the interaction, but the identity of the chosen MDP is not revealed to the agent. We first show that a general instance of LMDPs requires at least $Ω((SA)^M)$ episodes to even approximate the optimal policy. Then, we consider sufficient assumptions under which learning good policies requires polynomial number of episodes. We show that the key link is a notion of separation between the MDP system dynamics. With sufficient separation, we provide an efficient algorithm with local guarantee, {\it i.e.,} providing a sublinear regret guarantee when we are given a good initialization. Finally, if we are given standard statistical sufficiency assumptions common in the Predictive State Representation (PSR) literature (e.g., Boots et al.) and a reachability assumption, we show that the need for initialization can be removed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Contextual Blocking Bandits

We study a novel variant of the multi-armed bandit problem, where at each time step, the player observes an independently sampled context that determines the arms&#39; mean rewards. However, playing an arm blocks it (across all contexts) for a fixed and known number of future time steps. The above contextual setting, which captures important scenarios such as recommendation systems or ad placement with diverse users, invalidates greedy solution techniques that are effective for its non-contextual counterpart (Basu et al., NeurIPS19). Assuming knowledge of the context distribution and the mean reward of each arm-context pair, we cast the problem as an online bipartite matching problem, where the right-vertices (contexts) arrive stochastically and the left-vertices (arms) are blocked for a finite number of rounds each time they are matched. This problem has been recently studied in the full-information case, where competitive ratio bounds have been derived. We focus on the bandit setting, where the reward distributions are initially unknown; we propose a UCB-based variant of the full-information algorithm that guarantees a $\mathcal{O}(\log T)$-regret w.r.t. an $α$-optimal strategy in $T$ time steps, matching the $Ω(\log(T))$ regret lower bound in this setting. Due to the time correlations caused by blocking, existing techniques for upper bounding regret fail. For proving our regret bounds, we introduce the novel concepts of delayed exploitation and opportunistic subsampling and combine them with ideas from combinatorial bandits and non-stationary Markov chains coupling.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning Mixtures of Graphs from Epidemic Cascades

We consider the problem of learning the weighted edges of a balanced mixture of two undirected graphs from epidemic cascades. While mixture models are popular modeling tools, algorithmic development with rigorous guarantees has lagged. Graph mixtures are apparently no exception: until now, very little is known about whether this problem is solvable. To the best of our knowledge, we establish the first necessary and sufficient conditions for this problem to be solvable in polynomial time on edge-separated graphs. When the conditions are met, i.e., when the graphs are connected with at least three edges, we give an efficient algorithm for learning the weights of both graphs with optimal sample complexity (up to log factors). We give complimentary results and provide sample-optimal (up to log factors) algorithms for mixtures of directed graphs of out-degree at least three, for mixture of undirected graphs of unbalanced and/or unknown priors.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions

We consider a covariate shift problem where one has access to several different training datasets for the same learning problem and a small validation set which possibly differs from all the individual training distributions. This covariate shift is caused, in part, due to unobserved features in the datasets. The objective, then, is to find the best mixture distribution over the training datasets (with only observed features) such that training a learning algorithm using this mixture has the best validation performance. Our proposed algorithm, ${\sf Mix\&Match}$, combines stochastic gradient descent (SGD) with optimistic tree search and model re-use (evolving partially trained models with samples from different mixture distributions) over the space of mixtures, for this task. We prove simple regret guarantees for our algorithm with respect to recovering the optimal mixture, given a total budget of SGD evaluations. Finally, we validate our algorithm on two real-world datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Robust Estimation of Tree Structured Ising Models

We consider the task of learning Ising models when the signs of different random variables are flipped independently with possibly unequal, unknown probabilities. In this paper, we focus on the problem of robust estimation of tree-structured Ising models. Without any additional assumption of side information, this is an open problem. We first prove that this problem is unidentifiable, however, this unidentifiability is limited to a small equivalence class of trees formed by leaf nodes exchanging positions with their neighbors. Next, we propose an algorithm to solve the above problem with logarithmic sample complexity in the number of nodes and polynomial run-time complexity. Lastly, we empirically demonstrate that, as expected, existing algorithms are not inherently robust in the proposed setting whereas our algorithm correctly recovers the underlying equivalence class.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Robust Structured Statistical Estimation via Conditional Gradient Type Methods

Structured statistical estimation problems are often solved by Conditional Gradient (CG) type methods to avoid the computationally expensive projection operation. However, the existing CG type methods are not robust to data corruption. To address this, we propose to robustify CG type methods against Huber&#39;s corruption model and heavy-tailed data. First, we show that the two Pairwise CG methods are stable, i.e., do not accumulate error. Combined with robust mean gradient estimation techniques, we can therefore guarantee robustness to a wide class of problems, but now in a projection-free algorithmic framework. Next, we consider high dimensional problems. Robust mean estimation based approaches may have an unacceptably high sample complexity. When the constraint set is a $\ell_0$ norm ball, Iterative-Hard-Thresholding-based methods have been developed recently. Yet extension is non-trivial even for general sets with $O(d)$ extreme points. For setting where the feasible set has $O(\text{poly}(d))$ extreme points, we develop a novel robustness method, based on a new condition we call the Robust Atom Selection Condition (RASC). When RASC is satisfied, our method converges linearly with a corresponding statistical error, with sample complexity that scales correctly in the sparsity of the problem, rather than the ambient dimension as would be required by any approach based on robust mean estimation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The EM Algorithm gives Sample-Optimality for Learning Mixtures of Well-Separated Gaussians

We consider the problem of spherical Gaussian Mixture models with $k \geq 3$ components when the components are well separated. A fundamental previous result established that separation of $Ω(\sqrt{\log k})$ is necessary and sufficient for identifiability of the parameters with polynomial sample complexity (Regev and Vijayaraghavan, 2017). In the same context, we show that $\tilde{O} (kd/ε^2)$ samples suffice for any $ε\lesssim 1/k$, closing the gap from polynomial to linear, and thus giving the first optimal sample upper bound for the parameter estimation of well-separated Gaussian mixtures. We accomplish this by proving a new result for the Expectation-Maximization (EM) algorithm: we show that EM converges locally, under separation $Ω(\sqrt{\log k})$. The previous best-known guarantee required $Ω(\sqrt{k})$ separation (Yan, et al., 2017). Unlike prior work, our results do not assume or use prior knowledge of the (potentially different) mixing weights or variances of the Gaussian components. Furthermore, our results show that the finite-sample error of EM does not depend on non-universal quantities such as pairwise distances between means of Gaussian components.

0 citations0 reviewsNo code linkedOpen access