arXiv:2507.07580v2 Announce Type: replace Abstract: Recent studies suggest that context-aware low-rank approximation is a useful tool for compression and fine-tuning of modern large-scale neural networks. In this type of approximation, a norm is weighted by a matrix of input activations,…
arXiv:2512.12325v2 Announce Type: replace Abstract: We prove that a classic sub-Gaussian mixture proposed by Robbins in a stochastic setting actually satisfies a path-wise (deterministic) regret bound. For every path in a natural “Ville event” $E_alpha$, this regret till time $T$…
arXiv:2601.09865v1 Announce Type: new Abstract: Large Language Models (LLMs) enable advanced natural language processing but face deployment challenges on resource-constrained edge devices due to high computational, memory, and energy demands. Optimizing these models requires addressing three key challenges: acquiring task-specific…
arXiv:2601.09926v1 Announce Type: new Abstract: Most language-based assistants follow a reactive ask-and-respond paradigm, requiring users to explicitly state their needs. As a result, relevant but unexpressed needs often go unmet. Existing proactive agents attempt to address this gap either by…
arXiv:2601.09831v1 Announce Type: new Abstract: In this work, we provide a new convergence theory for plug-and-play proximal gradient descent (PnP-PGD) under prior mismatch where the denoiser is trained on a different data distribution to the inference task at hand. To…
arXiv:2601.09841v1 Announce Type: new Abstract: When training machine learning (ML) models for potential deployment in a healthcare setting, it is essential to ensure that they do not replicate or exacerbate existing healthcare biases. Although many definitions of fairness exist, we…
arXiv:2601.09825v1 Announce Type: new Abstract: We establish a lower bound on the eluder dimension of generalised linear model classes, showing that standard eluder dimension-based analysis cannot lead to first-order regret bounds. To address this, we introduce a localisation method for…
arXiv:2601.09809v1 Announce Type: new Abstract: Organizations and enterprises across domains such as healthcare, finance, and scientific research are increasingly required to extract collective intelligence from distributed, siloed datasets while adhering to strict privacy, regulatory, and sovereignty requirements. Federated Learning (FL)…
arXiv:2601.09776v1 Announce Type: new Abstract: As black box models and pretrained models gain traction in time series applications, understanding and explaining their predictions becomes increasingly vital, especially in high-stakes domains where interpretability and trust are essential. However, most of the…
arXiv:2502.10510v3 Announce Type: replace Abstract: Modern machine learning pipelines are increasingly combining and mixing data from diverse and disparate sources, e.g., pre-training large language models. Yet, finding the optimal data mixture is a challenging and open problem. We formalize this…
