arXiv research

Study finds a linear lower bound on conformal dimension for random hyperbolic groups.

Proposes rounding method for precise treatment effect estimation under budget constraints.

Most traditional online learning algorithms are based on variants of mirror descent or follow-the-leader. In this paper, we present an online algorithm based on a completely different approach, tailored for transductive settings, which combines "random playout" and randomized rounding of loss subgradients. As an applic…

We present and analyze a simple, two-step algorithm to approximate the optimal solution of the sparse PCA problem. Our approach first solves a L1 penalized version of the NP-hard sparse PCA optimization problem and then uses a randomized rounding strategy to sparsify the resulting dense solution. Our main theoretical r…

We prove a Chern-Lashof type formula computing the expected number of critical points of smooth function on a smooth manifold $M$ randomly chosen from a finite dimensional subspace $V\subset C^\infty(M)$ equipped with a Gaussian probability measure. We then use this formula this formula to find the asymptotics of the e…

New model tackles interference in online experiments.

Face recognition systems are vulnerable to composite face reconstruction attacks.

Improved cumulative regret for sequence prediction with limited expert advice.

Improves sampling, rounding, and integration of logconcave functions.

Unified framework for combinatorial and rounding algorithms in experimental design.

A new reinforcement learning method improves Max-Cut solutions without needing training data.

Recently, there has been an increasing interest in designing distributed convex optimization algorithms under the setting where the data matrix is partitioned on features. Algorithms under this setting sometimes have many advantages over those under the setting where data is partitioned on samples, especially when the …

Motivated by problems in search and detection we present a solution to a Combinatorial Multi-Armed Bandit (CMAB) problem with both heavy-tailed reward distributions and a new class of feedback, filtered semibandit feedback. In a CMAB problem an agent pulls a combination of arms from a set $\{1,...,k\}$ in each round, g…

A new mechanism reduces expert belief regret in online forecasting.

We propose an online algorithm for cumulative regret minimization in a stochastic multi-armed bandit. The algorithm adds $O(t)$ i.i.d. pseudo-rewards to its history in round $t$ and then pulls the arm with the highest average reward in its perturbed history. Therefore, we call it perturbed-history exploration (PHE). Th…

We consider the stochastic multi-armed bandit (MAB) problem in a setting where a player can pay to pre-observe arm rewards before playing an arm in each round. Apart from the usual trade-off between exploring new arms to find the best one and exploiting the arm believed to offer the highest reward, we encounter an addi…

The paper improves bandit algorithms by incorporating random-effect models.

A new algorithm for resource-aware multi-armed bandits minimizes regret.

We study the question of whether parallelization in the exploration of the feasible set can be used to speed up convex optimization, in the local oracle model of computation. We show that the answer is negative for both deterministic and randomized algorithms applied to essentially any of the interesting geometries and…

Novel unsupervised random forests improve density estimation and data synthesis.

We present DUAL-LOCO, a communication-efficient algorithm for distributed statistical estimation. DUAL-LOCO assumes that the data is distributed according to the features rather than the samples. It requires only a single round of communication where low-dimensional random projections are used to approximate the depend…

We study two randomized algorithms for generalized linear bandits. The first, GLM-TSL, samples a generalized linear model (GLM) from the Laplace approximation to the posterior distribution. The second, GLM-FPL, fits a GLM to a randomly perturbed history of past rewards. We analyze both algorithms and derive $\tilde{O}(…

New method reduces distributed non-convex optimization rounds and bits.

In this paper, we consider a class of finite-sum convex optimization problems defined over a distributed multiagent network with $m$ agents connected to a central server. In particular, the objective function consists of the average of $m$ ($\ge 1$) smooth components associated with each network agent together with a s…

Sparse random networks reduce communication in federated learning.

Gradient descent with biased rounding errors converges faster under certain conditions.

Algorithm allocates perishable resources online to minimize envy and inefficiency.

The design and performance analysis of bandit algorithms in the presence of stage-wise safety or reliability constraints has recently garnered significant interest. In this work, we consider the linear stochastic bandit problem under additional \textit{linear safety constraints} that need to be satisfied at each round.…

DSVGD improves federated learning with fewer communication rounds.

Round surgery diagrams represent 3-manifolds in $S^3$.

FedShuffle improves local updates in FL, especially with data imbalance.

New method certifies images against transformations like rotations and translations.

Contact round surgeries on $(\mathbb{S}^3,ξ_{st})$ help in constructing and understanding contact 3-manifolds.

In this article, we extend Huisken's theorem that convex surfaces flow to round points by mean curvature flow. We construct certain classes of mean convex and non-mean convex hypersurfaces that shrink to round points and use these constructions to create pathological examples of flows. We find a sequence of flows that …

In this paper we study the limitations of parallelization in convex optimization. A convenient approach to study parallelization is through the prism of \emph{adaptivity} which is an information theoretic measure of the parallel runtime of an algorithm [BS18]. Informally, adaptivity is the number of sequential rounds a…

Optimizes sample and round complexity in adaptive sampling from multiple distributions.

Consider an analytic map of a neighborhood of 0 in a vector space to a Euclidean space. Suppose that this map takes all germs of lines passing through 0 to germs of circles. Such a map is called rounding. We introduce a natural equivalence relation on roundings and prove that any rounding, whose differential at 0 has r…

New findings show infinitely many knots cannot be smoothly round handle slices.

We discuss the integrability of orthogonal almost complex structures on Riemannian products of even-dimensional round spheres and give a partial answer to the question raised by E. Calabi concerning the existence of complex structures on a product manifold of a round 2-sphere and a round 4-sphere.

A new algorithm finds minimizers in dueling optimization with a monotone adversary.

MOL-TS uses Thompson Sampling for multi-objective linear bandits with Pareto guarantees.

This work investigates how multi-round reasoning improves LLM performance.

CORe uses randomization to explore bandit problems without external noise.

New findings on $κ$-solutions with round cylinder as asymptotic shrinker.

Round balls minimize liquid drop model volumes ≤ 1.

Gradient descent stagnates in low-precision, but unbiased rounding schemes improve convergence.

Round cylinders are rigid in Ricci shrinkers close to the standard product.

We find new bounds on the conformal dimension of small cancellation groups. These are used to show that a random few relator group has conformal dimension 2+o(1) asymptotically almost surely (a.a.s.). In fact, if the number of relators grows like l^K in the length l of the relators, then a.a.s. such a random group has …