We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-…
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
48 results for “zooming algorithm”
The paper tackles multi-player information asymmetry bandits in metric spaces.
problem Information asymmetry in rewards, actions, or both in multiplayer bandit problems.
method Adopted CAB and zooming algorithms for information asymmetry in rewards and actions.
result Regret bounds of the same order in all 3 problem settings.
Study shows reinforcement learning algorithm's performance depends on metric space's size.
problem Continuous state and action spaces with metrics.
method Refined analysis of Sinclair et al. (2019) algorithm.
result Regret scales with the zooming dimension, a new parameter capturing near optimal actions.
We present a reinforcement learning approach for detecting objects within an image. Our approach performs a step-wise deformation of a bounding box with the goal of tightly framing the object. It uses a hierarchical tree-like representation of predefined region candidates, which the agent can zoom in on. This reduces t…
Much of the community detection literature studies structural communities, communities defined solely by the connectivity patterns of the network. Often, networks contain additional metadata which can inform community detection such as the grade and gender of students in a high school social network. In this work, we i…
New algorithm tackles delayed feedback in Lipschitz bandits with sublinear regret.
problem Delayed feedback in Lipschitz bandits.
method Design of algorithms for bounded and unbounded stochastic delays.
result Sublinear regret guarantees for both bounded and unbounded delays.
Improved adaptive rates for Lipschitz bandit problem.
problem Sequentially maximize an unknown Lipschitz function with noisy evaluations.
method Characterizes regret through integrals of suboptimality gaps over level sets, adapting to local growth.
result Improved adaptive rates strictly improving over classical zooming bounds.
In this paper we propose the multi-objective contextual bandit problem with similarity information. This problem extends the classical contextual bandit problem with similarity information by introducing multiple and possibly conflicting objectives. Since the best arm in each objective can be different given the contex…
ZoomRL learns efficient strategies for large state-action spaces using a metric.
problem Handling large state-action spaces in reinforcement learning.
method ZoomRL leverages continuous bandits to adaptively discretize the joint space.
result Achieves worst-case regret of $ ilde{O}(H^{ rac{5}{2}} K^{ rac{d+1}{d+2}})$.
We explore two techniques which use color to make sense of statistical text models. One method uses in-text annotations to illustrate a model's view of particular tokens in particular documents. Another uses a high-level, "words-as-pixels" graphic to display an entire corpus. Together, these methods offer both zoomed-i…
The paper tackles high-dimensional Bayesian optimization using tree-structured additive models.
problem Scaling Bayesian Optimization to high-dimensional problems.
method Tree-structured additive models with hybrid graph learning and zooming-based algorithms.
result Demonstrates faster model learning and reduced model complexity in high-dimensional settings.
Adaptive-treed banditsmath.ST
We describe a novel algorithm for noisy global optimisation and continuum-armed bandits, with good convergence properties over any continuous reward function having finitely many polynomial maxima. Over such functions, our algorithm achieves square-root regret in bandits, and inverse-square-root error in optimisation, …
Adaptive Discretization against an Adversary: Lipschitz bandits, Dynamic Pricing, and Auction Tuningcs.LG
Algorithm tackles adaptive discretization in adversarial Lipschitz bandits for dynamic pricing and auctions.
problem Adaptive discretization in adversarial Lipschitz bandits.
method Adversarial Zooming algorithm for adaptive discretization.
result First algorithm for adversarial Lipschitz bandits with instance-dependent regret bounds.
New extensions for homogeneous distributions on deformations to the normal cone.
problem Extending homogeneous distributions on a specific geometric structure.
method Using the zoom action and Meyer's results on weakly homogeneous distributions.
result All homogeneous extensions of distributions on the DNC are described.
Study shows how steepest descent algorithms' geometric margin increases during training.
problem Understanding implicit bias in steepest descent algorithms for neural networks.
method Analysis of steepest descent algorithms with infinitesimal learning rates in homogeneous neural networks.
result Limit points of training trajectories correspond to KKT points of margin-maximization problems.
Parallel surrogate optimization algorithms have proven to be efficient methods for solving expensive noisy optimization problems. In this work we develop a new parallel surrogate optimization algorithm (ProSRS), using a novel tree-based "zoom strategy" to improve the efficiency of the algorithm. We prove that if ProSRS…
We recently proposed a new ensemble clustering algorithm for graphs (ECG) based on the concept of consensus clustering. We validated our approach by replicating a study comparing graph clustering algorithms over benchmark graphs, showing that ECG outperforms the leading algorithms. In this paper, we extend our comparis…
New method controls generative models with continuous factors.
problem Lack of control over generative models and poor understanding of latent space.
method Introduces a method to find meaningful directions in latent space for precise control of generated images.
result Demonstrates effectiveness of method for GANs and variational auto-encoders.
Automated video conferencing system improves user experience with ASD and VC.
problem Improve remote video conferencing experience through automated speaker detection and virtual cinematography.
method Uses 4K wide-FOV camera, depth camera, and microphone array to extract features and train machine learning models for ASD and VC.
result System performs within 0.3 MOS of an expert cinematographer, as rated by users.
Study lenient regret and good-action identification in Gaussian process bandits.
problem Optimizing function values above a certain threshold in Gaussian process bandits.
method Study lenient regret notions and introduce algorithms for finding good actions.
result Upper and lower bounds on lenient regret for GP-UCB and elimination algorithms.
Simplifies large action space bandits by selecting representative actions.
problem Efficiently managing large action spaces with correlated outcomes.
method Random sampling and solving of bandit instances to identify representative actions.
result The algorithm selects a smaller set of representative actions that perform nearly as well as the full action space.
Cohomology fractalsmath.GT
Cohomology fractals are visual representations of cohomology classes on hyperbolic 3-manifolds.
problem Visualizing cohomology classes on hyperbolic 3-manifolds.
method Cohomology fractals are images associated to cohomology classes. They are related to limit sets of Kleinian groups but differ in key aspects. An implementation using ideal triangulations and ray-casting is presented.
result Cohomology fractals allow for real-time zooming in any direction at arbitrary depth.
RandQL is a new model-free algorithm for MDPs with a novel learning rate randomization approach.
problem Minimizing regret in episodic MDPs with model-free methods.
method Randomized Q-learning with learning rate randomization.
result RandQL achieves optimal regret bounds in both tabular and metric state-action spaces.
Algorithm learns diffusion processes with high-dimensional state spaces.
problem Stochastic control of unbounded diffusion processes with high-dimensional state spaces.
method Adaptive partitioning and learning algorithm that refines discretization based on estimation bias and statistical confidence.
result Established regret bounds that depend on problem parameters, extending to unbounded diffusion processes.
Learning Clustered Representation for Complex Free Energy Landscapescond-mat.stat-mech
In this paper we first analyzed the inductive bias underlying the data scattered across complex free energy landscapes (FEL), and exploited it to train deep neural networks which yield reduced and clustered representation for the FEL. Our parametric method, called Information Distilling of Metastability (IDM), is end-t…
In this paper we present a review of the existing typologies of Internet service users. We zoom in on social networking services including blogs and crowdsourcing websites. Based on the results of the analysis of the considered typologies obtained by means of FCA we developed a new user typology of a certain class of I…
Requirements elicitation can be very challenging in projects that require deep domain knowledge about the system at hand. As analysts have the full control over the elicitation process, their lack of knowledge about the system under study inhibits them from asking related questions and reduces the accuracy of requireme…
Unified analysis of tree-based methods for online reinforcement learning.
problem Designing efficient algorithms for online reinforcement learning with low sample complexity, storage, and computational burden.
method Unified theoretical analysis of tree-based hierarchical partitioning methods for online reinforcement learning.
result Our algorithms provide guarantees that scale with respect to the 'zooming dimension', improving upon ambient dimension scaling.
We study the problem of identifying different behaviors occurring in different parts of a large heterogenous network. We zoom in to the network using lenses of different sizes to capture the local structure of the network. These network signatures are then weighted to provide a set of predicted labels for every node. W…
Paper argues context equals environment, improving AI generalization.
problem AI models struggle to generalize in new environments.
method In-Context Risk Minimization (ICRM) algorithm.
result ICRM leads to significant out-of-distribution performance improvements.
A new framework tunes hyperparameters in real-time for contextual bandits.
problem Optimizing hyperparameters for contextual bandits in real-time.
method CDT (Continuous Dynamic Tuning) framework using Zooming TS algorithm.
result Achieves sublinear regret and performs better than existing methods.
New model allows sparse graphs with many triangles to be represented.
problem Sparse graphs with many triangles cannot be accurately represented in finite dimensions.
method Infinite-dimensional inner product model with manifold representations.
result Local neighborhoods can be represented in lower dimensions.
Sparse data models, where data is assumed to be well represented as a linear combination of a few elements from a dictionary, have gained considerable attention in recent years, and their use has led to state-of-the-art results in many signal and image processing tasks. It is now well understood that the choice of the …
We consider rough stochastic volatility models where the driving noise of volatility has fractional scaling, in the "rough" regime of Hurst parameter . This regime recently attracted a lot of attention both from the statistical and option pricing point of view. With focus on the latter, we sharpen the large de…
New algorithm reduces regret for single-index bandits to nearly optimal.
problem Optimizing rewards from unknown projections of high-dimensional contexts.
method Two-phase algorithm: estimate projection direction, reduce to 1D bandit, use UCB.
result Achieved optimal regret of .
Improved regret for single-index bandits with optimal algorithm.
problem Optimizing rewards from unknown one-dimensional projections of high-dimensional contexts.
method Two-phase algorithm: first estimate projection direction, then discretize and use UCB.
result Achieved optimal regret of .
Study shows how 'crowding' in equity trading affects performance and costs.
problem Deterioration of strategy performance, increased trading costs, and systemic risk due to equity factor crowding.
method Direct metrics of crowding based on imbalances of trades executed on the market, analyzing U.S. equity market data.
result Significant signs of crowding in well-known equity signals, especially Momentum, affecting order flow and portfolio rebalancing.
Probabilistic STNs improve image classification and robustness.
problem Training and robustness issues in STNs.
method Probabilistic extension of STNs that estimates stochastic transformations.
result Improved classification performance, robustness, and model calibration.
Recently, impressive denoising results have been achieved by Bayesian approaches which assume Gaussian models for the image patches. This improvement in performance can be attributed to the use of per-patch models. Unfortunately such an approach is particularly unstable for most inverse problems beyond denoising. In th…
Anti-correlated noise improves machine learning model generalization.
problem Improving machine learning model generalization.
method Injecting anticorrelated noise into gradient descent steps.
result Anti-correlated noise leads to better model generalization than uncorrelated noise.
Zooming into market statesq-fin.ST
We analyze the daily stock data of the Nasdaq Composite index in the 22-year period 1992-2013 and identify market states as clusters of correlation matrices with similar correlation structures. We investigate the stability of the correlation structure of each state by estimating the statistical fluctuations of correlat…
Bayesian approach helps update deep models without forgetting past data.
problem Updating deep models sequentially without forgetting past data.
method Bayesian inference for continual learning.
result Bayesian approach enables updating model beliefs with new data.
Unsupervised method discovers interpretable directions in GAN latent space.
problem Discovering interpretable directions in GAN latent space without supervision.
method Model-agnostic procedure to identify directions corresponding to semantic manipulations.
result Findings include directions for background removal and competitive saliency detection performance.
The paper analyzes Random Search and introduces BLiN-MOS for bandit learning.
problem Understanding and optimizing hyperparameter tuning in metric measure spaces.
method Introducing scattering dimension to quantify performance, and developing BLiN-MOS for bandit learning.
result Random Search converges to optimal values with specific rates in noise-free and noisy environments.
A new method corrects for bias in selecting the best candidate.
problem Bias in selecting the best candidate leads to invalid conclusions.
method Zoom correction, flexible for parametric and nonparametric settings.
result Valid inference on the winner is possible, even with selection bias.
Lead/lag relationships are an important stylized fact at high frequency. Some assets follow the path of others with a small time lag. We provide indicators to measure this phenomenon using tick-by-tick data. Strongly asymmetric cross-correlation functions are empirically observed, especially in the future/stock case. W…
The goal of this study is to present the development of a machine learning based approach that utilizes phase space alone to separate the Gaia DR2 stars into two categories: those accreted onto the Milky Way from those that are in situ. Traditional selection methods that have been used to identify accreted stars typica…
Analysis of histopathology slides is a critical step for many diagnoses, and in particular in oncology where it defines the gold standard. In the case of digital histopathological analysis, highly trained pathologists must review vast whole-slide-images of extreme digital resolution ( pixels) across multiple…