Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

73146219292 · Jun 202019922001200920182026
48 results for Randomized rounding

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

problem Resource-constrained experimental design for precise treatment effect estimation.
method Dependent randomized rounding procedure to convert assignment probabilities into binary treatment decisions.
result Improved estimator precision through variance reduction and efficient inference.

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…

2011-06-13abs ↗pdf ↗

We prove a Chern-Lashof type formula computing the expected number of critical points of smooth function on a smooth manifold MM randomly chosen from a finite dimensional subspace VC(M)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…

2010-08-30abs ↗pdf ↗

Face recognition systems are vulnerable to composite face reconstruction attacks.

problem Vulnerability of face recognition systems to composite face reconstruction attacks.
method Assumed attacker uses composite face parts to reconstruct faces faster and more efficiently.
result Current face recognition systems are extremely vulnerable to random search attacks.

Improved cumulative regret for sequence prediction with limited expert advice.

problem Minimizing cumulative regret in sequence prediction with limited information.
method Convex combination of experts with limited observation, achieving constant regret.
result Strategies achieve constant regret independent of the horizon T, improving over standard bounds.

Unified framework for combinatorial and rounding algorithms in experimental design.

problem Designing and analyzing combinatorial and rounding algorithms for experimental design problems.
method Local search framework for combinatorial algorithms and regret minimization framework for rounding algorithms.
result Unified approach to match and improve all known results in D/A/E-design and obtain new results in unknown settings.

A new compression technique reduces communication costs in distributed deep learning.

problem Communication bottlenecks in distributed deep learning training.
method Natural Compression (NC) and Natural Dithering.
result Natural Compression increases communication savings by 3-4 times with negligible convergence speed impact.

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

problem Max-Cut problem is NP-hard, and existing methods struggle with generalizability and scalability.
method Training-data-free reinforcement learning approach to hyperplane rounding for Max-Cut optimization.
result Our method consistently achieves better Max-Cut solutions across various graph types.

A new mechanism reduces expert belief regret in online forecasting.

problem Minimizing expert belief regret in strategic forecasting.
method Developed a no-regret mechanism for non-myopic experts using online I-ELF.
result Achieved ildeO(TN) ilde{O}(\sqrt{T N}) regret for full-information setting.

DUAL-LOCO uses random projections for efficient distributed statistical estimation.

problem Efficiently estimating statistical models in distributed systems.
method DUAL-LOCO employs low-dimensional random projections to approximate feature dependencies across workers.
result DUAL-LOCO achieves bounded approximation error with error bounds dependent weakly on the number of workers.

New research shows parallel optimization is ineffective for convex problems.

problem The inefficiency of parallel optimization methods for convex problems.
method Lower bounds analysis in the local oracle model of computation.
result Parallel and randomized algorithms cannot speed up convex optimization in various geometries and objective functions.

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

problem Optimizing resource usage in a multi-armed bandit problem with censored observations.
method UCB-inspired online learning algorithm with theoretical regret analysis.
result The proposed algorithm outperforms standard multi-armed bandit algorithms in simulations.

New algorithm tackles CMAB with filtered feedback, achieving O(ln(n))\mathcal{O}(\ln(n)) regret.

problem Sequential search and detection problems with hidden true rewards.
method Robust-F-CUCB algorithm, balancing exploration and exploitation.
result Upper confidence bound algorithm with O(ln(n))\mathcal{O}(\ln(n)) regret bound.

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

problem Improving statistical efficiency in multi-armed bandit problems with misspecified priors.
method Introduces a random-effect model to bandits, estimating arm means and designing a UCB algorithm ReUCB.
result Derives an upper bound on the Bayes regret of ReUCB, showing improved performance over Thompson sampling.

Novel unsupervised random forests improve density estimation and data synthesis.

problem Density estimation and data synthesis for complex tabular data.
method Recursive unsupervised random forests with alternating generation and discrimination rounds.
result Provable consistency and smooth densities with fast execution.

The paper sets communication limits for distributed optimization with feature-based data partitions.

problem Understanding communication limits in distributed convex optimization with feature-based data partitions.
method Developed tight lower bounds on communication rounds for non-incremental and incremental algorithms.
result Established communication limits for a broad class of algorithms under feature-based data partitioning.

PHE adds pseudo-rewards to history to minimize regret in stochastic bandits.

problem Minimizing cumulative regret in stochastic multi-armed bandits.
method PHE algorithm that adds O(t)O(t) i.i.d. pseudo-rewards to history and pulls the best arm based on the perturbed history.
result Near-optimal regret bounds derived for PHE.

Algorithm allocates perishable resources online to minimize envy and inefficiency.

problem Online allocation of perishable resources to minimize envy and inefficiency.
method Algorithm uses predictions of perishing order and desired envy bound to adaptively allocate resources.
result Algorithm achieves optimal envy-efficiency trade-off as derived from strong lower bounds.

DSVGD improves federated learning with fewer communication rounds.

problem Federated learning scalability and trustworthiness.
method Distributed Stein Variational Gradient Descent (DSVGD) for non-parametric Bayesian inference.
result DSVGD achieves comparable accuracy and scalability to other methods, with well-calibrated predictions.

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

problem Stagnation or negative impact of rounding errors in neural network training with low precision.
method Analysis of gradient descent with stochastic fixed-point rounding errors under the Polyak-Lojasiewicz inequality.
result Biased rounding errors can improve convergence rates, especially when the Polyak-Lojasiewicz inequality holds.

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

problem Data imbalance in FL leads to different clients performing different numbers of local updates.
method FedShuffle incorporates random reshuffling, data imbalance, and client sampling.
result FedShuffle improves upon FL methods that assume homogeneous updates in heterogeneous setups.

New algorithm reduces complexity for distributed and stochastic optimization.

problem Optimization of distributed and stochastic problems with multiple agents.
method Random Gradient Extrapolation Method (RGEM)
result Achieves optimal complexity bounds for both distributed and stochastic optimization.

The study extends Huisken's theorem to nonconvex surfaces that shrink to round points.

problem Extending Huisken's theorem to nonconvex surfaces.
method Constructing mean convex and non-mean convex hypersurfaces, using mean curvature flow.
result Found pathological examples of flows and sequences of flows that shrink to round points.

New method certifies images against transformations like rotations and translations.

problem Certifying robustness of images against transformations like rotations and translations.
method Randomized smoothing with three different kinds of defenses.
result Individual certificates can be obtained via statistical error bounds or efficient online inverse computation.

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

problem Finding minimizers in dueling optimization with a monotone adversary.
method Introduces and studies dueling optimization with a monotone adversary, designs an efficient randomized algorithm.
result Efficient algorithm incurs cost O(d)O(d) and iteration complexity O(dlog(1/ε)2)O(d\log(1/\varepsilon)^2), asymptotically optimal.

Contact round surgeries on (S3,ξst)(\mathbb{S}^3,ξ_{st}) help in constructing and understanding contact 3-manifolds.

problem Constructing contact 3-manifolds using Legendrian surgeries.
method Introducing contact round surgeries of indices 1 and 2, and associating them with surgery diagrams.
result Every closed connected contact 3-manifold can be obtained by a sequence of contact round surgeries on Legendrian knots in (S3,ξst)(\mathbb{S}^3,ξ_{st}).

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

problem Optimizing multiple conflicting objectives in linear contextual bandits.
method Proposes MOL-TS, a Thompson Sampling algorithm with Pareto regret guarantees.
result Achieves a worst-case Pareto regret bound of O~(d3/2T)\widetilde{O}(d^{3/2}\sqrt{T}).

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

problem Adaptive sampling from multiple distributions with limited rounds and samples.
method Introduces OODS framework and analyzes tradeoffs between sample and round complexity.
result Achieves near-optimal sample complexity and sub-polynomial round complexity.

Contact round surgery proves existence of contact structures on 3-manifolds.

problem Existence of contact structures on 3-manifolds.
method Contact round surgery and Lutz twist/Giroux torsion operations.
result Any contact structure on a closed orientable 3-manifold is constructed from the standard contact structure on the 3-sphere via contact round surgeries.

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…

2002-12-06abs ↗pdf ↗

Safe algorithm for linear bandits with safety constraints, matching previous results.

problem Designing safe bandit algorithms with linear safety constraints.
method Linear Thompson Sampling with frequentist regret analysis.
result Frequentist regret of order O(d3/2log1/2dT1/2log3/2T)\mathcal{O} (d^{3/2}\log^{1/2}d \cdot T^{1/2}\log^{3/2}T).

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

problem Improving problem-solving abilities in complex tasks with LLMs.
method Investigates approximation, learnability, and generalization properties of multi-round auto-regressive models.
result Transformers with finite context windows are universal approximators for Turing-computable functions and can approximate any Turing-computable sequence-to-sequence function through multi-round reasoning.