# Ksurf-Drone: Attention Kalman Filter for Contextual Bandit Optimization in Cloud Resource Allocation

arXiv: https://arxiv.org/abs/2511.09766 · HTML: https://mlsanity.com/paper/2511.09766/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 54 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Builds on (most cited first, 12 of 12)

- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [DRAW: A Recurrent Neural Network For Image Generation](https://mlsanity.com/paper/1502.04623/) (2015)
- [KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics](https://mlsanity.com/paper/2107.10043/) (2021)
- [Structured Attention Networks](https://mlsanity.com/paper/1702.00887/) (2017)
- [Lipschitz Bandits: Regret Lower Bounds and Optimal Algorithms](https://mlsanity.com/paper/1405.4758/) (2014)
- [Adaptive Gaussian Processes on Graphs via Spectral Graph Wavelets](https://mlsanity.com/paper/2110.12752/) (2021)
- [GSP-KalmanNet: Tracking Graph Signals via Neural-Aided Kalman Filtering](https://mlsanity.com/paper/2311.16602/) (2023)
- [How Does Variance Shape the Regret in Contextual Bandits?](https://mlsanity.com/paper/2410.12713/) (2024)
- [Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference](https://mlsanity.com/paper/2411.01036/) (2024)
- [On Computational Complexity Reduction Methods for Kalman Filter Extensions](https://mlsanity.com/paper/1512.03077/) (2015)
- [Lifting the Fog of Uncertainties: Dynamic Resource Orchestration for the Containerized Cloud](https://mlsanity.com/paper/2309.16962/) (2023)
- [Ksurf: Attention Kalman Filter and Principal Component Analysis for Prediction under Highly Variable Cloud Workloads](https://mlsanity.com/paper/2406.18801/) (2024)

## Built on by (most cited first, 1 of 1)

- [Learning to Attack: A Bandit Approach to Adversarial Context Poisoning](https://mlsanity.com/paper/2603.00567/) (2026)

## Abstract (arXiv)

Resource orchestration and configuration parameter search are key concerns for container-based infrastructure in cloud data centers. Large configuration search space and cloud uncertainties are often mitigated using contextual bandit techniques for resource orchestration including the state-of-the-art Drone orchestrator. Complexity in the cloud provider environment due to varying numbers of virtual machines introduces variability in workloads and resource metrics, making orchestration decisions less accurate due to increased nonlinearity and noise. Ksurf, a state-of-the-art variance-minimizing estimator method ideal for highly variable cloud data, enables optimal resource estimation under conditions of high cloud variability. This work evaluates the performance of Ksurf on estimation-based resource orchestration tasks involving highly variable workloads when employed as a contextual multi-armed bandit objective function model for cloud scenarios using Drone. Ksurf enables significantly lower latency variance of 41% at p95 and 47% at p99, demonstrates a 4% reduction in CPU usage and 7 MB reduction in master node memory usage on Kubernetes, resulting in a 7% cost savings in average worker pod count on VarBench Kubernetes benchmark.