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.

168,742 papers · 148 categories

Trend · papers per month

150300449599 · Jun 202019922001200920172026
48 results for sampling zeros

A new model synthesizes population with fewer structural and sampling zeros.

problem Synthesizing a feasible and diverse synthetic population from limited data.
method A deep generative model with two regularizations to minimize structural zeros and preserve sampling zeros.
result The model significantly improves feasibility and diversity of synthetic populations.

Randomly sampled interpolators achieve zero generalization error with enough data.

problem Understanding the high generalization ability of machine learning models.
method Algebraic geometry tools to prove zero generalization error for random interpolators.
result Generalization error of randomly sampled interpolators becomes zero once the number of training samples exceeds a geometric threshold.

We present a new family of zero-field Ising models over NN binary variables/spins obtained by consecutive "gluing" of planar and O(1)O(1)-sized components and subsets of at most three vertices into a tree. The polynomial-time algorithm of the dynamic programming type for solving exact inference (computing partition func…

2019-10-22abs ↗pdf ↗

M2M tackles zero-shot structured noise suppression in images.

problem Structured noise with strong anisotropic correlations in real-world images.
method M2M introduces a novel sampling strategy that generates pseudo-independent sub-image pairs from a single noisy input, using directional interpolation and generalized median filtering.
result M2M consistently outperforms state-of-the-art zero-shot methods under correlated noise.

Paper studies MCCR models with scale parameters tending to zero, revealing optimal learning rate and comparing robustness.

problem Analyzing MCCR models with scale parameters approaching zero.
method Investigates MCCR models with scale parameters tending to zero, revealing optimal learning rate and comparing robustness.
result Optimal learning rate of MCCR models is O(n1){\mathcal{O}}(n^{-1}) in the asymptotic sense.

The paper analyzes the efficiency of gradient estimation methods in noisy function evaluations.

problem Estimating gradients of smooth functions using noisy function evaluations.
method Information-theoretic lower bounds and finite difference method analysis.
result The finite difference method is not minimax optimal, suggesting room for improvement in gradient estimation.

With the recent renaissance of deep convolution neural networks, encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient training data and fully annotated training data. However, to scale the recognition to a large number of classes with few or now training samp…

2017-10-13abs ↗pdf ↗

The paper addresses score-mismatched diffusion models and zero-shot conditional samplers.

problem Theoretical guarantees for score-mismatched diffusion models in zero-shot conditional sampling.
method Theoretical analysis of score-mismatched diffusion models and zero-shot conditional samplers.
result Theoretical performance guarantees with explicit dimensional dependencies for score-mismatched diffusion samplers.

Paper introduces S-SSE for stable sparse subspace embedding.

problem Inefficient sparse random projection matrices with uneven non-zero distribution.
method Uses uniform sampling without replacement to create a stable sparse subspace embedded matrix (S-SSE).
result S-SSE maintains Euclidean distance better after dimension reduction.

Phylogenetic tree inference using deep DNA sequencing is reshaping our understanding of rapidly evolving systems, such as the within-host battle between viruses and the immune system. Densely sampled phylogenetic trees can contain special features, including "sampled ancestors" in which we sequence a genotype along wit…

2018-05-28abs ↗pdf ↗

Study best-response learning dynamics in zero-sum polymatrix games under full and minimal information settings.

problem Learning dynamics in zero-sum polymatrix games under different information settings.
method Two-timescale learning dynamics combining smoothed best-response updates and TD-learning for estimating local payoff functions.
result Polynomial-time finite-sample guarantees for convergence to an ε-Nash equilibrium in the minimal information case.

We call an Ising model tractable when it is possible to compute its partition function value (statistical inference) in polynomial time. The tractability also implies an ability to sample configurations of this model in polynomial time. The notion of tractability extends the basic case of planar zero-field Ising models…

2018-12-22abs ↗pdf ↗

We consider the problem of selecting non-zero entries of a matrix AA in order to produce a sparse sketch of it, BB, that minimizes AB2\|A-B\|_2. For large m×nm \times n matrices, such that nmn \gg m (for example, representing nn observations over mm attributes) we give sampling distributions that exhibit four importa…

2013-11-19abs ↗pdf ↗

This paper optimizes model-based RL for two-player zero-sum games with near-optimal sample complexity.

problem Optimizing model-based reinforcement learning for two-player zero-sum games with minimal samples.
method Model-based reinforcement learning approach for two-player discounted zero-sum Markov games with a generative model.
result Achieves a sample complexity of ildeO(SAB(1γ)3ε2) ilde O(|S||A||B|(1-γ)^{-3}ε^{-2}) for finding the Nash equilibrium and ε-NE policies.

We consider general non-Euclidean distance measures between real world objects that need to be classified. It is assumed that objects are represented by distances to other objects only. Conditions for zero-error dissimilarity based classifiers are derived. Additional conditions are given under which the zero-error deci…

2016-01-18abs ↗pdf ↗

Dissertation tackles zero-shot anomaly detection, focusing on consistent anomalies and proposing CoDeGraph framework.

problem Consistent anomalies bias distance-based zero-shot anomaly detection methods.
method Formalized consistent anomalies, identified similarity scaling and neighbor-burnout phenomena, introduced CoDeGraph framework.
result CoDeGraph effectively suppresses consistent anomalies in zero-shot anomaly detection.

New algorithm finds near-optimal policies efficiently in zero-sum games.

problem Lack of provable efficiency guarantees for policy optimization in zero-sum games.
method Policy optimization algorithm with function approximation.
result Proves efficient convergence to near-optimal policies with polynomial samples and iterations.

We study the Thompson sampling algorithm in an adversarial setting, specifically, for adversarial bit prediction. We characterize the bit sequences with the smallest and largest expected regret. Among sequences of length TT with k<T2k < \frac{T}{2} zeros, the sequences of largest regret consist of alternating zeros and …

2019-06-21abs ↗pdf ↗

The paper develops algorithms for competitive RL in partially observable MGs.

problem Challenges in reinforcement learning with function approximation and partial observability.
method Proposes posterior sampling methods for self-play and adversarial learning in zero-sum MGs.
result Developed algorithms achieve low regret bounds scaling sublinearly with GEC and episode number.

Pessimistic model-based algorithm finds Nash equilibria in zero-sum Markov games from offline data.

problem Learning Nash equilibria in two-player zero-sum Markov games from limited data.
method Pessimistic model-based algorithm with Bernstein-style lower confidence bounds (VI-LCB-Game).
result Proves sample complexity no larger than CclippedS(A+B)(1γ)3ε2\frac{C_{\mathsf{clipped}}^\star S(A+B)}{(1-γ)^3 \varepsilon^2}, achieving minimax optimality.

We introduce the isoperimetric loss as a regularization criterion for learning the map from a visual representation to a semantic embedding, to be used to transfer knowledge to unknown classes in a zero-shot learning setting. We use a pre-trained deep neural network model as a visual representation of image data, a Wor…

2019-03-15abs ↗pdf ↗

New algorithm improves sample efficiency for zero-sum Markov games.

problem Improving sample efficiency for model-free algorithms in zero-sum Markov games.
method Proposes a model-free stage-based Q-learning algorithm using variance reduction techniques.
result Achieves optimal sample complexity for finding ε-optimal Nash Equilibrium.

New method improves mHealth user engagement using Thompson sampling for count data.

problem Optimizing mHealth interventions for distal outcomes through proximal context.
method Combines count data models with Thompson sampling for contextual bandits.
result Improves user engagement in mHealth trials compared to existing methods.

Develops a method for non-equilibrium importance sampling to estimate expectations and constants.

problem Estimating expectations and normalization constants for complex high-dimensional distributions.
method Generates samples from a base distribution, transports them using a velocity field, and averages along flowlines.
result The method can achieve zero-variance estimation and significantly reduces variance compared to vanilla estimators.

There are two major paradigms of white-box adversarial attacks that attempt to impose input perturbations. The first paradigm, called the fix-perturbation attack, crafts adversarial samples within a given perturbation level. The second paradigm, called the zero-confidence attack, finds the smallest perturbation needed …

2019-10-01abs ↗pdf ↗

Paper proposes a method to break symmetries in Bayesian matrix factorization.

problem Symmetries in posterior distribution reduce MCMC sampling efficiency.
method Modification to Gaussian prior mean and covariance to break symmetries.
result Breaking symmetries leads to lower autocorrelation and reconstruction errors.

Learning to classify unseen class samples at test time is popularly referred to as zero-shot learning (ZSL). If test samples can be from training (seen) as well as unseen classes, it is a more challenging problem due to the existence of strong bias towards seen classes. This problem is generally known as \emph{generali…

2019-09-10abs ↗pdf ↗

Paper develops efficient algorithms for zero-sum Markov games with general function classes.

problem Challenging settings in zero-sum Markov games with parameterized value functions or models.
method Developed new model-free and model-based algorithms for decoupled and coordinated settings.
result Improved sample complexity and regret bounds for various settings.

Aggregates diverse zero-shot LLM outputs for better corporate disclosure classification.

problem Combining varied zero-shot LLM predictions for improved stock return prediction.
method Multi-prompt framework with three fixed zero-shot LLM classifiers, logistic meta-classifier aggregation.
result Aggregated model outperforms single classifiers and baseline models, increasing balanced accuracy from 0.566 to 0.606.

Zero-shot contrastive loss improves text-guided image style transfer without extra training.

problem Stochastic nature of diffusion models leads to trade-offs between style transformation and content preservation.
method Proposes a zero-shot contrastive loss for diffusion models that doesn't require additional fine-tuning or auxiliary networks.
result Method outperforms existing methods while preserving content and requiring no additional training.

Develops a cross-lingual hate speech detection model using pre-trained Transformers.

problem Detecting hate speech in low-resource languages.
method Utilizes frozen Transformer language models and AXEL attention-based classification block for zero-shot and few-shot learning.
result Demonstrates highly competitive results on English and Spanish subsets of the HatEval challenge.

Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier learning stage, a task also known as zero-shot learning. We propose a novel zero-shot l…

2014-10-14abs ↗pdf ↗

We define a new class of irreducible groups, called groups not infinite-index presentable by products or not IIPP. We prove that certain aspherical manifolds with fundamental groups not IIPP do not admit maps of non-zero degree from direct products. This extends previous results of Kotschick and Loeh, providing new cla…

2015-07-28abs ↗pdf ↗

This paper establishes conditions for sparse signal recovery with sparse measurements.

problem Recovering the support of a sparse signal using noisy projections with sparse measurement matrices.
method Establishes sufficient conditions for successful sparse recovery using sparse measurement matrices.
result A phase transition threshold for sparse recovery in the sparse setting is discovered, revealing a trade-off between sampling complexity and measurement sparsity.