6 papers
Fast segmentation of watermarked texts from large language models through an epidemic change-point framework
Soham Bonnerjee, Subhrajyoty Roy, Sayar Karmakar
With the growing use of large language models, concerns over content authenticity have spurred a variety of watermarking schemes. These schemes use secret keys to detect machine-ge…
Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite Moments
Qianqian Lei, Soham Bonnerjee, Yuefeng Han +1
While algorithmic stability is a central tool for understanding generalization of learning algorithms, existing high-probability guarantees typically rely on uniform boundedness or…
Sharp Gaussian approximations for Decentralized Federated Learning
Soham Bonnerjee, Sayar Karmakar, Wei Biao Wu
Federated Learning has gained traction in privacy-sensitive collaborative environments, with local SGD emerging as a key optimization method in decentralized settings. While its co…
Sharp asymptotic theory for Q-learning with LDTZ learning rate and its generalization
Soham Bonnerjee, Zhipeng Lou, Wei Biao Wu
Despite the sustained popularity of Q-learning as a practical tool for policy determination, a majority of relevant theoretical literature deals with either constant ($η_{t}\equiv…
Fast localization of anomalous patches in spatial data under dependence
Soham Bonnerjee, Sayar Karmakar, George Michailidis
We propose a scalable, provably accurate method for localizing an unknown number of multiple axis-aligned anomalous patches in spatial data under a general class of spatial depende…
How Private is Your Attention? Bridging Privacy with In-Context Learning
Soham Bonnerjee, Zhen Wei, Yeon +3
In-context learning (ICL)-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models.…