no code implementations • 1 Mar 2024 • Zirui Yan, Dennis Wei, Dmitriy Katz-Rogozhnikov, Prasanna Sattigeri, Ali Tajer
First, the structural causal models (SCMs) are assumed to be unknown and drawn arbitrarily from a general class $\mathcal{F}$ of Lipschitz-continuous functions.
no code implementations • 1 Feb 2024 • Burak Varici, Emre Acartürk, Karthikeyan Shanmugam, Abhishek Kumar, Ali Tajer
The paper addresses both the identifiability and achievability aspects.
no code implementations • 17 Jan 2024 • Anmol Dwivedi, Santiago Paternain, Ali Tajer
This paper considers the sequential design of remedial control actions in response to system anomalies for the ultimate objective of preventing blackouts.
no code implementations • 30 Oct 2023 • Zirui Yan, Arpan Mukherjee, Burak Varici, Ali Tajer
Cumulative regret is adopted as the design criteria, based on which the objective is to design a sequence of interventions that incur the smallest cumulative regret with respect to an oracle aware of the entire causal model and its fluctuations.
1 code implementation • 24 Oct 2023 • Burak Varici, Emre Acartürk, Karthikeyan Shanmugam, Ali Tajer
For identifiability, the paper establishes that perfect recovery of the latent causal model and variables is guaranteed under uncoupled interventions.
no code implementations • 20 Oct 2023 • P. N. Karthik, Vincent Y. F. Tan, Arpan Mukherjee, Ali Tajer
It is shown that under every policy, the state-action visitation proportions satisfy a specific approximate flow conservation constraint and that these proportions match the optimal proportions dictated by the lower bound under any asymptotically optimal policy.
1 code implementation • 3 Sep 2023 • Jiajin Zhang, Hanqing Chao, Amit Dhurandhar, Pin-Yu Chen, Ali Tajer, Yangyang Xu, Pingkun Yan
To accomplish this challenging task, first, a spectral sensitivity map is introduced to characterize the generalization weaknesses of models in the frequency domain.
no code implementations • 15 Mar 2023 • Anmol Dwivedi, Ali Tajer
The search process is formalized as a partially observable Markov decision process (POMDP), which is subsequently solved via a time-varying graph recurrent neural network (GRNN) that judiciously accounts for the inherent temporal and spatial structures of the data generated by the system.
no code implementations • 19 Jan 2023 • Burak Varici, Emre Acarturk, Karthikeyan Shanmugam, Abhishek Kumar, Ali Tajer
The objectives are: (i) recovering the unknown linear transformation (up to scaling) and (ii) determining the directed acyclic graph (DAG) underlying the latent variables.
no code implementations • 10 Jan 2023 • Arpan Mukherjee, Ali Tajer
Two key metrics for assessing bandit algorithms are computational efficiency and performance optimality (e. g., in sample complexity).
1 code implementation • 1 Dec 2022 • Jiajin Zhang, Hanqing Chao, Amit Dhurandhar, Pin-Yu Chen, Ali Tajer, Yangyang Xu, Pingkun Yan
Domain generalization (DG) aims to train a model to perform well in unseen domains under different distributions.
1 code implementation • 26 Aug 2022 • Burak Varici, Karthikeyan Shanmugam, Prasanna Sattigeri, Ali Tajer
Two linear mechanisms, one soft intervention and one observational, are assumed for each node, giving rise to $2^N$ possible interventions.
no code implementations • 10 Aug 2022 • Arpan Mukherjee, Ali Tajer, Pin-Yu Chen, Payel Das
Additionally, each process $i\in\{1, \dots, K\}$ has a private parameter $\alpha_i$.
no code implementations • 22 Jul 2022 • Arpan Mukherjee, Ali Tajer
Based on this test statistic, a BAI algorithm is designed that leverages the canonical sequential probability ratio tests for arm selection and is amenable to tractable analysis for the exponential family of bandits.
no code implementations • NeurIPS 2021 • Arpan Mukherjee, Ali Tajer, Pin-Yu Chen, Payel Das
Owing to the adversarial contamination of the rewards, each arm's mean is only partially identifiable.
1 code implementation • NeurIPS 2021 • Burak Varici, Karthikeyan Shanmugam, Prasanna Sattigeri, Ali Tajer
This paper considers the problem of estimating the unknown intervention targets in a causal directed acyclic graph from observational and interventional data.
no code implementations • NeurIPS 2021 • Arpan Mukherjee, Ali Tajer, Pin-Yu Chen, Payel Das
Owing to the adversarial contamination of the rewards, each arm's mean is only partially identifiable.
no code implementations • 18 Jan 2021 • Ali Tajer, Avi Steiner, Shlomo Shamai
However, when the variations are infrequent, their temporal average can deviate significantly from the channel's ergodic mode, rendering a lack of instantaneous performance guarantees.
Information Theory Information Theory
no code implementations • NeurIPS 2019 • Saurabh Sihag, Ali Tajer
Leveraging such side information can be abstracted as inferring structures of distinct graphical models that are {\sl partially} similar.