Introduces tensor bandits for multi-dimensional online decision making.
problem Optimal decision making in multi-dimensional online scenarios.
method Stochastic low-rank tensor bandits, tensor elimination, tensor epoch-greedy, tensor ensemble sampling.
result Tensor elimination and tensor epoch-greedy algorithms outperform existing methods.
Algorithm reduces high-dimensional SLB regret by exploiting hidden low-rank structure.
problem High-dimensional stochastic linear bandits with hidden low-rank structure.
method Projective Stochastic Linear Bandit (PSLB) using PCA projection.
result PSLB achieves tighter regret bound and faster convergence.
Study multi-task learning with low-rank representation in stochastic linear bandits.
problem Transfer learning across multiple linear bandit tasks with shared low-dimensional representation.
method Proposes a greedy policy with trace norm regularization to implicitly learn a low-rank representation without knowing the rank.
result Upper bound on multi-task regret of N d T ( T + d ) r \sqrt{NdT(T+d)r} N d T ( T + d ) r , showing benefit over independent task solving. An algorithm finds the maximum entry of a stochastic low-rank matrix from noisy observations.
problem Finding the maximum entry of a stochastic low-rank matrix from sequential observations.
method LowRankElim algorithm, which is a statistical approach to find the maximum entry of a non-negative matrix.
result An upper bound on the regret of $O((K + L) \poly(d) Δ^{-1} \log n)$ , where K K K and L L L are the number of rows and columns, d d d is the rank of the matrix, and Δ Δ Δ is the minimum gap. New algorithm improves learning efficiency in multi-task contextual bandits.
problem Improving learning efficiency in multi-task contextual bandits.
method Alternating projected gradient descent (GD) and minimization estimator for low-rank feature matrix recovery.
result Proved regret bound for multi-task learning algorithm.
Unified framework for high-dimensional bandit problems with low-dimensional structures.
problem Stochastic high-dimensional bandit problems with low-dimensional structures.
method Proposed a simple unified algorithm and a general analysis framework for the regret upper bound.
result Unified algorithm achieves comparable regret bounds in various high-dimensional bandit problems.
Algorithm for low-rank matrix bandits with heavy-tailed rewards, achieving nearly optimal regret bound.
problem Stochastic low-rank matrix bandit with heavy-tailed rewards.
method LOTUS algorithm using truncation and dynamic exploration.
result Regret bound of order $ ilde O(d^ rac{3}{2}r^ rac{1}{2}T^ rac{1}{1+δ}/ ilde{D}_{rr})$ without knowing T T T . Novel method for efficient low-rank matrix estimation and bandit algorithms.
problem Low-rank matrix estimation and bandit problems.
method LowPopArt method for low-rank matrix estimation and novel experimental design criterion.
result Improved recovery guarantees and regret bounds for low-rank bandit algorithms.
New framework improves efficiency in low-rank matrix bandit problems.
problem Stochastic contextual low-rank matrix bandit problem with unknown rank matrices.
method G-ESTT and G-ESTS frameworks using Stein's method and regularization.
result Achieved improved regret bounds for low-rank matrix bandit problems.
New algorithm tackles bilinear bandit problem with low-rank structure.
problem Finding the optimal action in a bilinear bandit problem with low-rank reward matrix.
method Two-stage algorithm: subspace exploration followed by linear bandit refinement.
result Regret bound of ESTR is O ~ ( ( d 1 + d 2 ) 3 / 2 r T ) \widetilde{\mathcal{O}}((d_1+d_2)^{3/2} \sqrt{r T}) O (( d 1 + d 2 ) 3/2 r T ) . An algorithm tackles low-rank linear bandit problems with improved regret bounds.
problem Low-rank linear bandit problems where rewards are inner products with an unknown low-rank matrix.
method Combines online-to-confidence-set conversion and exponentially weighted average forecaster with a covering of low-rank matrices.
result Achieves O ~ ( ( d 1 + d 2 ) 3 / 2 r T ) \widetilde{O}((d_1+d_2)^{3/2}\sqrt{rT}) O (( d 1 + d 2 ) 3/2 r T ) regret, improving over standard bounds when r ≪ min { d 1 , d 2 } r \ll \min\{d_1,d_2\} r ≪ min { d 1 , d 2 } . Paper introduces G-LowTESTR for efficient tensor bandits.
problem Efficient decision-making in multi-dimensional data with non-linear reward functions.
method Generalized low-rank tensor contextual bandits model and G-LowTESTR algorithm.
result G-LowTESTR achieves superior regret bound compared to vectorization and matricization methods.
The paper tackles pure exploration in multi-armed bandits with low rank structure using oblivious sampling.
problem Pure exploration in multi-armed bandits with low rank reward sequences.
method The approach involves separating the exploration strategy from feedback, using oblivious sampling, and incorporating kernel information of reward vectors.
result Efficient algorithms with regret bound O ( d ( ln N ) / n ) O(d\sqrt{(\ln N)/n}) O ( d ( ln N ) / n ) for both time-varying and fixed cases, with a lower bound gap of O ( ln N ) O(\sqrt{\ln N}) O ( ln N ) . Develops TOFU for tensor bandits with low-rank structure.
problem Linear bandit models fail to capture high-dimensional, low-rank tensor structures.
method Develops TOFU, a tensor bandit algorithm that estimates low-dimensional subspaces and uses norm constraints.
result Improves regret bound by a multiplicative factor that grows exponentially in system order.
Unified approach tackles high-dimensional tensor bandits with convex optimization and weakly decomposable regularizers.
problem Challenges in high-dimensional generalized tensor bandits where existing algorithms fail.
method Proposes a generalized linear tensor bandits algorithm with a unified analytical framework using convex optimization and weakly decomposable regularizers.
result Unified analytical framework provides better bounds and broader applicability compared to existing methods.
Efficient algorithms for low-rank bandits using subspace recovery.
problem Contextual bandits with low-rank reward matrices.
method Spectral methods for subspace recovery, reformulating as linear bandits.
result Nearly optimal policy evaluation and best policy identification, minimax guarantees for regret minimization.
New method for dynamic pricing with many products using low-rank demand structure.
problem Maximizing revenue in dynamic pricing with many products and evolving demand.
method Online bandit convex optimization with side information from observed demands, using low-rank structure of demand model.
result Revenue maximization approaches that of the best fixed price vector in hindsight, with rate dependent on demand model rank.
New algorithm tackles dynamic query routing to multiple embedding models.
problem Dynamic query routing to multiple embedding models under adversarial conditions.
method Formalized as adversarial contextual linear bandit with low-rank experts, proposed HPG algorithm.
result HPG algorithm achieves linearized policy regret of i l d e O ( s M T ) ilde{\mathcal O}(s\sqrt{M T}) i l d e O ( s M T ) . Paper presents a reduction-based framework for conservative bandits and RL with improved lower and upper bounds.
problem Conservative bandits and reinforcement learning problems.
method Reduction technique to calculate necessary and sufficient budget from baseline policy.
result Improved lower and upper bounds for various conservative settings.
New algorithm catches moving subspaces in bandit problems.
problem Adapt to changing low-dimensional latent subspaces in bandit settings.
method Piecewise-stationary low-rank linear contextual bandits with CUSUM-style boundary detection.
result Achieves intrinsic rank dynamic regret rate of O ( r T ) O(r\sqrt{T}) O ( r T ) . Efficiently learns neural network parameters from streaming data.
problem Online learning of neural networks from non-stationary data streams.
method Low-rank extended Kalman filtering for approximate Bayesian inference.
result Significantly faster learning and adaptation to changing distributions.
New spectral methods improve matrix estimation in RL with low-rank structure.
problem Estimating matrices with low-rank structure in reinforcement learning.
method Spectral-based matrix estimation approaches.
result Spectral methods efficiently recover singular subspaces and minimize entry-wise error.
New algorithms minimize regret in multi-task and lifelong linear bandits with shared representation.
problem Minimizing regret in multi-task and lifelong linear bandits with shared representation.
method Novel algorithms using efficient estimator for low-rank linear feature extractor and novel analysis.
result Achieved regret bounds matching minimax lower bound up to logarithmic factors.
We consider a stochastic continuum armed bandit problem where the arms are indexed by the ℓ 2 \ell_2 ℓ 2 ball B d ( 1 + ν ) B_{d}(1+ν) B d ( 1 + ν ) of radius 1 + ν 1+ν 1 + ν in R d \mathbb{R}^d R d . The reward functions r : B d ( 1 + ν ) → R r :B_{d}(1+ν) \rightarrow \mathbb{R} r : B d ( 1 + ν ) → R are considered to intrinsically depend on k ≪ d k \ll d k ≪ d unknown linear parameters so that $r(\mathbf{x}) = g(\ma…
The stochastic linear bandit problem proceeds in rounds where at each round the algorithm selects a vector from a decision set after which it receives a noisy linear loss parameterized by an unknown vector. The goal in such a problem is to minimize the (pseudo) regret which is the difference between the total expected …
Optimizes algorithms for non-concave bandit problems.
problem Optimizing algorithms for non-concave bandit problems.
method Unified zeroth-order optimization paradigm.
result Minimax-optimal algorithms in the dimension for low-rank generalized linear bandit problems.
Stochastic gradient descent on manifolds improves low-rank approximation.
problem Efficiently approximate large matrices with lower rank.
method Stochastic gradient descent on a manifold.
result Algorithm outperforms Euclidean space methods on Netflix Prize data.
Paper solves stochastic contextual linear bandits using linear bandit algorithms.
problem Stochastic contextual linear bandits with unknown context distribution.
method Establishes a reduction framework to convert to linear bandit problems.
result Achieves nearly optimal regret bound of O ( d T log T ) O(d\sqrt{T\log T}) O ( d T log T ) . Optimal algorithm for identifying best arm in stochastic linear bandits with fixed confidence.
problem Identifying the best arm in stochastic linear bandits with fixed confidence.
method Extending an algorithm designed for Best Arm Identification to the ε ε ε -Thresholding Bandit Problem (TBP). result Asymptotically optimal algorithm for TBP.
A meta-UCB method combines stochastic bandit algorithms.
problem Combining multiple stochastic bandit algorithms efficiently.
method Meta-UCB procedure solving an N-armed bandit problem.
result Final regret depends only on the best base algorithm's regret.
New method for online low-rank matrix completion with improved regret.
problem Designing an efficient algorithm for online recommendation systems with low regret.
method Explore-then-commit (ETC) approach and iterative user clustering (OCTAL) for rank-1 setting.
result Nearly optimal regret bounds for online low-rank matrix completion.
A new framework for structured bandits using influence diagrams and variational Thompson sampling.
problem Complex statistical dependencies in structured bandit problems.
method Influence diagram framework, variational Thompson sampling, tracking structured posterior distribution.
result Empirically evaluated algorithms perform as well as or better than existing baselines.
Jointly tackles assortment and pricing in retail, using bandit models.
problem Maximizing revenue or profit in retail through optimal assortment and pricing.
method Contextual bandits with a flexible, interpretable model for high-dimensional contexts and actions.
result Proves lower regret compared to state-of-the-art methods in various bandit and pricing models.
Paper studies attacks on bandit algorithms and shows how attackers can manipulate data to hijack behavior.
problem Potential attacks on bandit algorithms can cause catastrophic loss in real-world applications.
method Proposes a framework of offline and online attacks on bandit algorithms using convex optimization and adaptive strategies.
result Attackers can force bandit algorithms to pull target arms with high probability by manipulating data.
Improved algorithms for stochastic linear bandits using tighter confidence sequences.
problem Stochastic linear bandits with improved worst-case regret guarantees.
method Novel tail bound for adaptive martingale mixtures to construct tighter confidence sequences.
result Linear bandit algorithm achieves competitive worst-case regret.
New algorithm reduces regret from sqrt(T) to polylog(T) in stochastic contextual linear bandits.
problem Achieving logarithmic regret in stochastic contextual linear bandits.
method Low Regret Stochastic Contextual Bandits ( exttt{LR-SCB}) algorithm, exploiting stochastic contexts and parameter estimation.
result Logarithmic regret (polylog(T)) achieved, improving over sqrt(T) lower bound.
RONM method reduces regret in stochastic convex bandits with decreasing noise.
problem Stochastic convex bandit problem with decreasing noise.
method Regularized Online Newton Method (RONM) based on Online Newton Method (ONM).
result RONM achieves polylogarithmic regret in time horizon n.
New algorithm reduces regret in stochastic bandit convex optimization.
problem Optimizing decisions in uncertain environments with convex losses.
method Introduces a second-order method for zeroth-order stochastic convex bandits.
result Regret bound of ( 1 + r / d ) [ d 1.5 n + d 3 ] p o l y l o g ( n , d , r ) (1 + r/d)[d^{1.5} \sqrt{n} + d^3] polylog(n, d, r) ( 1 + r / d ) [ d 1.5 n + d 3 ] p o l y l o g ( n , d , r ) . Improved regret bounds for Tsallis-INF in adversarial bandits and corruptions.
problem Adversarial bandits and corruptions in multiarmed bandit problems.
method Improved regret bounds for Tsallis-INF algorithm.
result Achieves $\mathcal{O}\left(\left(\sum_{i
eq i^*} \frac{1}{Δ_i}
ight)\log_+\left(\frac{(K-1)T}{\left(\sum_{i
eq i^*} \frac{1}{Δ_i}
ight)^2}
ight)+\sqrt{C\left(\sum_{i
eq i^*}\frac{1}{Δ_i}
ight)\log_+\left(\frac{(K-1)T}{C\sum_{i
eq i^*}\frac{1}{Δ_i}}
ight)}
ight)$ regret bound.
A new algorithm reduces regret in cooperative multi-agent bandits with heavy-tailed data.
problem Cooperative multi-agent bandits with heavy-tailed data.
method MP-UCB algorithm incorporating robust estimation with message-passing protocol.
result Optimal regret bounds for MP-UCB in various settings.
Optimal semi-bandit algorithm for both stochastic and adversarial environments.
problem Optimal semi-bandit algorithm for both stochastic and adversarial environments.
method Developed a general semi-bandit algorithm that achieves O ( log T ) \mathcal{O}(\log T) O ( log T ) regret for stochastic and O ( T ) \mathcal{O}(\sqrt{T}) O ( T ) regret for adversarial environments without regime or T T T knowledge. result First algorithm to achieve optimal O ( log T ) \mathcal{O}(\log T) O ( log T ) and O ( T ) \mathcal{O}(\sqrt{T}) O ( T ) regret simultaneously for stochastic and adversarial environments. Combines multiple bandit algorithms to create a nearly optimal single algorithm.
problem Designing a single bandit algorithm that performs nearly as well as the best individual algorithm in a stochastic environment.
method Develops two general corralling algorithms that achieve favorable regret guarantees.
result The regret of the corralling algorithms is no worse than the best individual algorithm's performance.
Bayesian bandit algorithms with approximate inference improve regret bounds in stochastic linear bandits.
problem Theoretical justification for Bayesian bandit algorithms with approximate inference in stochastic linear bandits.
method Proposed a theoretical framework to analyze approximate inference impact and conducted frequentist regret analysis on LinTS and LinBUCB.
result LinTS and LinBUCB preserve their original regret upper bounds with larger constant terms in approximate inference settings.
New algorithm reduces regret in corrupted bandits.
problem Stochastic multi-armed bandits with adversarial corruption.
method A new algorithm that is agnostic to corruption levels.
result Regret is nearly optimal and can handle significant corruption.
New model for display advertising with stochastic and adversarial components.
problem Display advertising with stochastic and adversarial click-through-rates.
method Adversarial scaling model; two algorithms tested: action elimination and mirror descent.
result Two algorithms are robust to adversarial scaling.
Adversaries can manipulate bandit algorithms to control chosen actions.
problem Manipulating stochastic bandit algorithms to influence chosen actions.
method Proposes an attack against ε ε ε -greedy and UCB algorithms without knowing mean rewards. result Attackers can control actions with logarithmic effort, making it easy to hijack behavior.
We propose a method to infer stochastic low-rank RNNs from neural data.
problem Fitting low-rank RNNs to noisy, stochastic neural data.
method Variational sequential Monte Carlo methods for stochastic low-rank RNNs.
result Lower dimensional latent dynamics compared to state-of-the-art methods.
Paper tackles stochastic k k k -submodular bandits with full feedback, achieving sublinear regret.
problem Online optimization of k k k -submodular functions with full-bandit feedback. method Proposes online algorithms for various k k k -submodular stochastic combinatorial multi-armed bandit problems. result Achieves sublinear α α α -regret bounds for multiple k k k -submodular stochastic combinatorial multi-armed bandit problems.