Optimal algorithm reduces regret in adversarial bandit problem with multiple plays.
problem Minimizing regret in adversarial bandit problem with multiple plays.
method Introducing a new expert advice algorithm for multiple-play setting, achieving minimax optimal regret bounds.
result Minimizes regret asymptotically to the best switching strategy with optimal bounds.
Proposes DEXP3.M for unknown delay in multi-arm bandit with multiple play.
problem Unknown delays in adversarial multi-armed bandit with multiple play.
method DEXP3.M algorithm addressing the challenge of associating feedback losses to arms.
result Regret bound is only slightly worse than single play setting.
We discuss a multiple-play multi-armed bandit (MAB) problem in which several arms are selected at each round. Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically excellent performance, and it is revealed to have an optimal regret bound in the…
A budget-constrained multi-armed bandit problem with multiple plays is analyzed for both stochastic and adversarial settings.
problem Optimizing decisions in a multi-armed bandit problem with a budget constraint for multiple plays.
method Upper Confidence Bound (UCB) algorithm for stochastic case and an extension of Exp3 algorithm for adversarial case.
result Achieved regret bounds for both stochastic and adversarial settings.
We study a generalization of the multi-armed bandit problem with multiple plays where there is a cost associated with pulling each arm and the agent has a budget at each time that dictates how much she can expect to spend. We derive an asymptotic regret lower bound for any uniformly efficient algorithm in our setting. …
New algorithm for shareable arms with load-dependent rewards in stochastic bandits.
problem Learning optimal play strategy with shareable finite-capacity arms in stochastic bandits.
method Developed a capacity estimator and online learning algorithm for MP-MAB with shareable arms.
result Regret upper bound matches the lower bound, validating the algorithm's performance.
Proof of Donaldson's theorem using Seiberg-Witten equations for multiple spinors.
problem Donaldson's Diagonalization Theorem
method Abelian gauge-theoretic variant of Seiberg-Witten equations for multiple spinors
result Proof of Donaldson's Diagonalization Theorem
A new bandit algorithm for web page item display.
problem Optimizing item display at specific positions on a web page.
method Position-based multiple-play bandits with Thompson sampling.
result Delivers better recommendations with less prior information.
We prove several results on Almgren's multiple valued functions and their links to integral currents. In particular, we give a simple proof of the fact that a Lipschitz multiple valued map naturally defines an integer rectifiable current; we derive explicit formulae for the boundary, the mass and the first variations a…
The paper uses linear function approximators to bias MCTS for general games.
problem Improving MCTS playing strength for general games.
method Using linear function approximators with local features for self-play training.
result Significantly improved playing strength in multiple board games.
Investigates the fundamental components of attention mechanisms.
problem Understanding the building blocks of attention in deep learning.
method Classified and studied three key mechanisms: additive, multiplicative output, and synaptic attention.
result Additive activation attention is central in proofs of lower bounds.
Polynomial algorithm for multiplication on one-hole torus skein algebra.
problem Complexity of multiplicative structure in skein algebra.
method Provided a polynomial algorithm for one-hole torus.
result Closed form formulas for multiplication of curves with low crossing number.
Unified framework denoises data and abstains from uncertain predictions.
problem Data quality and predictive uncertainty in deep neural networks.
method Unified filtering framework leveraging data density.
result Framework outperforms state-of-the-art techniques in denoising and abstaining.
Ranked Reward algorithm improves bin packing performance.
problem Improving reinforcement learning for combinatorial optimization.
method Ranking rewards from self-play to create a relative performance metric.
result Ranked Reward algorithm outperforms other methods on bin packing problems.
Study optimal adaptive allocation for multi-armed bandits with Markovian rewards.
problem Optimal adaptive allocation for multi-armed bandits with Markovian rewards.
method Round-robin Kullback-Leibler upper confidence bounds for optimal adaptive allocation.
result Logarithmic dependence of regret on time horizon, asymptotically optimal.
We analyze a notion of multiple valued sections of a vector bundle over an abstract smooth Riemannian manifold, which was suggested by W. Allard in the unpublished note "Some useful techniques for dealing with multiple valued functions" and generalizes Almgren's Q-valued functions. We study some relevant properties o…
In this paper we analyze Gresham's Law, in particular, how the rate of inflow or outflow of currencies is affected by the demand elasticity of arbitrage and the difference in face value ratios inside and outside of a country under a bimetallic system. We find that these equations are very similar to those used to descr…
Optimizes financial decisions with illiquid assets using Kelly criterion.
problem Determining optimal betting strategies in games with external capital constraints.
method Dynamic programming and WKB approximation for multi-round games; Kelly criterion for single-round games.
result Rational players adjust their risk-taking based on the proportion of their capital locked away.
FGNNs improve game-playing AI by exploiting symmetries.
problem Symmetrical game states are not exploited by current AI.
method Introduces FGNNs for creating group-equivariant neural networks.
result FGNNs improve performance in games like checkers and image segmentation.
This paper relaxes the common prior assumption in the public and private information game of Morris and Shin (2000, 2004). For the generalized game, where the agent's prior expectations are heterogenous, it derives a sharp condition for the emergence of unique/multiple equilibria. This condition indicates that unique e…
Bayesian optimization improved AlphaGo's win-rate from 50% to 66.5%.
problem Hyper-parameter tuning for machine learning models.
method Bayesian optimization for hyper-parameter tuning.
result Bayesian optimization improved AlphaGo's performance in self-play games.
In a series of papers, including the present one, we give a new, shorter proof of Almgren's partial regularity theorem for area minimizing currents in a Riemannian manifold, with a slight improvement on the regularity assumption for the latter. This note establishes a new a priori estimate on the excess measure of an a…
The banking systems that deal with risk management depend on underlying risk measures. Following the Basel II accord, there are two separate methods by which banks may determine their capital requirement. The Value at Risk measure plays an important role in computing the capital for both approaches. In this paper we an…
Deep neural network solves large multi-agent games for Markovian Nash equilibrium.
problem Finding Markovian Nash equilibrium in large multi-agent stochastic differential games.
method Reformulate as decoupled decision problems, solve iteratively using deep BSDE method.
result Proposed algorithm accurately finds Nash equilibrium in large games.
A fundamental operation in many vision tasks, including motion understanding, stereopsis, visual odometry, or invariant recognition, is establishing correspondences between images or between images and data from other modalities. We present an analysis of the role that multiplicative interactions play in learning such …
Persona2vec learns multiple node roles in graphs.
problem Graphs often have nodes with multiple overlapping roles.
method Persona2vec learns multiple node representations based on structural contexts.
result Persona2vec outperforms state-of-the-art models in link prediction.
J-Play learns high-level feature representation from high-dimensional data.
problem Improving explainability, generalization, and cost-effectiveness in subspace learning.
method Joint and progressive learning of multi-coupled projections to linearize high-dimensional data.
result J-Play achieves superior multi-label classification performance.
This work introduces a method to learn dynamical systems from noisy sensor measurements using multiple shooting.
problem Learning dynamical systems from noisy sensor measurements is challenging due to system instability.
method A scalable method based on multiple shooting.
result Robust learning of latent representations of dynamical systems from noisy measurements.
Agents learn to play a first-person multiplayer game at human level performance.
problem Training AI agents for complex, multi-agent, real-time environments.
method Population-based deep reinforcement learning with concurrent training of multiple agents.
result Achieved human-level performance in a first-person multiplayer game.
New method estimates state-action stationary distribution for better off-policy policy evaluation.
problem Accurately estimating state-action stationary distribution for off-policy policy evaluation.
method Estimated Mixture Policy (EMP) for state and state-action stationary distribution corrections.
result Empirical validation shows improved accuracy over state-of-the-art methods.
The classification work [5], [9] left unsettled only those anomalous isoparametric hypersurfaces with four principal curvatures and multiplicity pair {4,5},{6,9} or {7,8} in the sphere. By systematically exploring the ideal theory in commutative algebra in conjunction with the geometry of isoparametric hypers…
BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.
problem Accurate inflation forecasting is challenging due to dynamic factors and the layered structure of the Consumer Price Index.
method Bi-directional Hierarchical Recurrent Neural Network (BiHRNN) model that uses bidirectional information flow between levels and informative constraints on RNN parameters.
result BiHRNN significantly outperforms traditional RNN models in forecasting accuracy.
Novel method uses information theory to measure causal influences during transient neural events.
problem Characterizing network interactions during transient neural events.
method Structural Causal Models, Information Theory, Transfer Entropy, Dynamic Causal Strength, Relative Dynamic Causal Strength.
result Introduced a novel measure, relative Dynamic Causal Strength, with theoretical and empirical support.
JAMPI improves matrix multiplication in Spark, boosting performance by up to 24%.
problem Efficiently performing matrix multiplication in Spark.
method Combining asynchronous network IO, auto-vectorization, and barrier execution mode.
result Up to 24% performance increase in distributed matrix multiplication.
The study examines how hyperparameters affect prediction discrepancies in machine learning models.
problem Prediction inconsistencies across different machine learning models trained on the same dataset.
method Investigation of six models (Elastic Net, Decision Tree, k-NN, SVM, RF, XGBoost) on 21 benchmark datasets, focusing on key hyperparameters.
result Hyperparameter tuning improves model performance but increases prediction discrepancies, especially in Extreme Gradient Boosting.
New EB methods handle correlated observations in the Normal Means problem.
problem Handling correlations in the Normal Means problem.
method Developed new EB methods based on Schwartzman's theory.
result New methods compare favorably with other methods in FDR control.
Fractal neural networks play SimCity and Conway's Game of Life on varying scales.
problem Generalizing agents' performance to larger gameboards than during training.
method Reinforcement learning in a custom environment, using fractal neural networks.
result Agents can generalize to larger gameboards, solving a minigame unsolvable with local strategies.
Fictitious play is a simple and widely studied adaptive heuristic for playing repeated games. It is well known that fictitious play fails to be Hannan consistent. Several variants of fictitious play including regret matching, generalized regret matching and smooth fictitious play, are known to be Hannan consistent. In …
Memory-enhanced self-play leads to faster exploration and better performance.
problem Faster exploration and better performance in reinforcement learning environments.
method Memory augmentation in self-play to store and reuse experience.
result Memory-augmented self-play agents outperform standard self-play agents.
Factorial moments are convenient tools in nuclear physics to characterize the multiplicity distributions when phase-space resolution (Δ) becomes small. For uncorrelated particle production within Δ, Gaussian statistics holds and factorial moments Fq are equal to unity for all orders q. Correlations between par…
Optimizes mobile notifications for multiple objectives using reinforcement learning.
problem Optimizing mobile notification systems for multiple objectives.
method End-to-end offline reinforcement learning with Double Deep Q-network and Conservative Q-learning.
result Demonstrates improved performance and benefits of the proposed approach.
Grimaldi-Pansu metrics are constructed for manifolds with multiple ends.
problem Volume growth on manifolds with more than one end.
method Constructing Riemannian metrics with bounded geometry and uniform bounds for volume growth.
result Uniform bounds for volume growth of Grimaldi-Pansu metrics in certain manifolds.
DoPaNet uses multiple discriminators to prevent mode collapse in GANs.
problem Mode collapse in adversarial training.
method Employing multiple discriminators and a classifier to guide the generator.
result DoPaNet effectively covers the target distribution and outperforms competing methods.
Enhanced feedback model improves sample-efficiency in POMDPs.
problem Exponential hardness of learning in POMDPs.
method Multiple observations in hindsight feedback model.
result Sample-efficient learning possible for new subclasses of POMDPs.
A new framework for controllable generation of discrete masked models.
problem Efficient controllable generation of discrete data models.
method Plug-and-play framework based on importance sampling.
result Demonstrates versatility across multiple domains, including protein design.
The standard theory of coherent risk measures fails to consider individual institutions as part of a system which might itself experience instability and spread new sources of risk to the market participants. In compliance with an approach adopted by Shapley and Shubik (1969), this paper proposes a cooperative market g…
Improved multi-task averaging reduces mean squared error in high-dimensional data.
problem Joint estimation of multiple distributions using independent data sets.
method Exploits similarities between tasks by shrinking naive estimators towards local averages.
result The method provides a significant reduction in mean squared error, especially in high-dimensional spaces.
Kernel methods are among the most popular techniques in machine learning. From a frequentist/discriminative perspective they play a central role in regularization theory as they provide a natural choice for the hypotheses space and the regularization functional through the notion of reproducing kernel Hilbert spaces. F…