3 citations · 3 across the 19 of their papers we have counts for
8 papers · 1 filter
CalTwin: Towards Calibrated, Shift-Robust Medical World Models via Fisher-Information Regularisation
Behraj Khan, Shabir Ahmad, Syed Ahmad Chan Bukhari +1
Medical world models aim to learn a latent state of patient or organ physiology and a transition function that forecasts how that state evolves under interventions, supporting down…
PIcsC: Partitioning-Induced Covariate Shift Correction
Behraj Khan, Behroz Mirza, Syed Ahmad Chan Bukhari +1
Covariate shift across training-data partitions biases model selection and parameter estimation in cross-validation, lifelong learning, and federated learning. We propose \textit{P…
Technical note on Fisher Information for Robust Federated Cross-Validation
Behraj Khan, Tahir Qasim Syed
When training data are fragmented across batches or federated-learned across different geographic locations, trained models manifest performance degradation. That degradation partl…
Technical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting
Behraj Khan, Tahir Qasim Syed
We present a theoretical framework for M-FISHER, a method for sequential distribution shift detection and stable adaptation in streaming data. For detection, we construct an expone…
Adapting to Fragmented and Evolving Data: A Fisher Information Perspective
Behraj Khan, Tahir Qasim Syed, Nouman Muhammad Durrani
Modern machine learning systems operating in dynamic environments often face \textit{sequential covariate shift} (SCS), where input distributions evolve over time while the conditi…
Efficient Learning Under Density Shift in Incremental Settings Using Cramér-Rao-Based Regularization
Behraj Khan, Behroz Mirza, Nouman Durrani +1
The continuous surge in data volume and velocity is often dealt with using data orchestration and distributed processing approaches, abstracting away the machine learning challenge…
Causal Covariate Shift Correction using Fisher information penalty
Behraj Khan, Behroz Mirza, Tahir Syed
Evolving feature densities across batches of training data bias cross-validation, making model selection and assessment unreliable (\cite{sugiyama2012machine}). This work takes a d…
Mitigating covariate shift in non-colocated data with learned parameter priors
Behraj Khan, Behroz Mirza, Nouman Durrani +1
When training data are distributed across{ time or space,} covariate shift across fragments of training data biases cross-validation, compromising model selection and assessment. W…