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.

168,786 papers · 148 categories

Trend · papers per month

0.3%0.5%0.8%0.2% · Jan 202519922001200920172026
27 results for Piecewise-Stationary

New algorithm detects changes in combinatorial semi-bandit rewards.

problem Detecting changes in piecewise-stationary reward distributions in combinatorial semi-bandits.
method Combination of CUCB algorithm and GLRT change-point detector.
result Regret bound of O(√(NKTlogT)) for piecewise-stationary combinatorial semi-bandits.

The problem of time-series clustering is considered in the case where each data-point is a sample generated by a piecewise stationary ergodic process. Stationary processes are perhaps the most general class of processes considered in non-parametric statistics and allow for arbitrary long-range dependence between variab…

2019-06-26abs ↗pdf ↗

Two algorithms improve performance in piecewise-stationary cascading bandits.

problem Real-world user preferences change over time, complicating stationary bandit models.
method Developed two algorithms, GLRT-CascadeUCB and GLRT-CascadeKL-UCB, using a change-point detector (GLRT).
result Regret upper bounds of O(NLTlogT)\mathcal{O}(\sqrt{NLT\log{T}}), improving on existing methods.

Algorithm identifies best arm in piecewise stationary linear bandits with minimal samples.

problem Identifying the best arm in a piecewise stationary linear bandit model with unknown contexts and changepoints.
method Design of PSε\varepsilonBAI+^+ algorithm, consisting of PSε\varepsilonBAI and Nε\varepsilonBAI subroutines.
result PSε\varepsilonBAI+^+ achieves optimal sample complexity up to a logarithmic factor.

Study adapts combinatorial semi-bandit for piecewise stationary, causally related rewards.

problem Nonstationary environment with changing base arms' distributions and causal relationships.
method Upper Confidence Bound (UCB) algorithm with change-point detector and group restart strategy.
result Regret upper bound reflecting effects of structural and distribution changes.

New algorithms detect changes in non-stationary MABs for better performance.

problem Non-stationary MAB environments where arm reward distributions change over time.
method Modular Detection Augmented Bandit (DAB) procedures with improved performance lower bounds.
result Modular DAB procedures achieve order-optimal regret bounds for various change detectors and bandit algorithms.

Study shows nonstationary bandits require T-dependent regret even with minimal nonstationarity.

problem Understanding satisficing regret in nonstationary multi-armed bandits.
method Developed a novel Fano-based framework for nonstationary bandits with a post-interaction reference construction.
result Optimal regret scales with T even with minimal nonstationarity, contrasting with stationary case.

Master algorithm fails to detect non-stationarity in practical settings.

problem Non-Stationary Reinforcement Learning without prior knowledge.
method Master algorithm tested under various conditions, including piecewise stationary multi-armed bandits.
result Master's non-stationarity detection is ineffective for practical horizons, leading to performance similar to random restarting.

Algorithm reduces decision-making errors in multi-agent bandit problems.

problem Minimizing decision errors in multi-agent multi-armed bandit problems.
method RBO-Coop-UCB algorithm with Bayesian change point detection.
result Expected group regret is upper bounded by O(KNMlogT+KMTlogT)\mathcal{O}(KNM\log T + K\sqrt{MT\log T}).

This paper introduces the Partition Tree Weighting technique, an efficient meta-algorithm for piecewise stationary sources. The technique works by performing Bayesian model averaging over a large class of possible partitions of the data into locally stationary segments. It uses a prior, closely related to the Context T…

2012-11-03abs ↗pdf ↗

Improved algorithm detects changes in RL environments with non-stationary MDPs.

problem Learning in non-stationary reinforcement learning environments.
method R-BOCPD-UCRL2 algorithm for MDPs with multinomial state transitions.
result Near-optimal theoretical guarantees in terms of false-alarm rate and detection delay.

Memory-based models can learn to approximate Bayes-optimal predictors for non-stationary data.

problem Learning from non-stationary data with unobserved switching points.
method Memory-based neural models, including Transformers, LSTMs, and RNNs, trained to minimize log loss.
result Memory-based models can accurately approximate known Bayes-optimal algorithms and perform Bayesian inference over latent switching points.

Adaptive beamforming collapses in highly non-stationary environments, but the Universal Switching Beamformer resolves this by dynamically adjusting memory length.

problem Adaptive beamforming performance degrades in highly non-stationary environments.
method Integrating sequential prediction into the beamforming architecture.
result The USB achieves agility and precision in tracking highly non-stationary scenes.

Selective reinitialization improves adaptability of neural bandits in dynamic environments.

problem Loss of plasticity in neural bandits, leading to rigid neural network parameters.
method Selective Reinitialization (SeRe) framework that dynamically resets underutilized units.
result SeRe enhances adaptability of CNB algorithms, reducing cumulative regret in dynamic environments.

New algorithm for nonstationary GLBs reduces computation and memory costs.

problem Nonstationary generalized linear bandits with unknown time-varying parameters.
method Discounted Online Mirror Descent (DOMD) for parameter estimation.
result Dynamic regret bounds of order O(1)O(1) per round in drifting and piecewise-stationary environments.