arXiv:2509.21711v1 Announce Type: new Abstract: As data collection and simulation capabilities advance, multi-modal learning, the task of learning from multiple modalities and sources of data, is becoming an increasingly important area of research. Surrogate models that learn from data of…
arXiv:2509.21866v1 Announce Type: new Abstract: Estimating the Conditional Average Treatment Effect (CATE) is often constrained by the high cost of obtaining outcome measurements, making active learning essential. However, conventional active learning strategies suffer from a fundamental objective mismatch. They are…
arXiv:2509.21707v1 Announce Type: new Abstract: Real-world applications often face scarce labeled data due to the high cost and time requirements of gold-standard experiments, whereas unlabeled data are typically abundant. With the growing adoption of machine learning techniques, it has become…
arXiv:2509.21614v1 Announce Type: new Abstract: We present a theoretical analysis of some popular adaptive Stochastic Gradient Descent (SGD) methods in the small learning rate regime. Using the stochastic modified equations framework introduced by Li et al., we derive effective continuous…
arXiv:2509.21584v1 Announce Type: new Abstract: Learning disentangled representations is a fundamental task in multi-modal learning. In modern applications such as single-cell multi-omics, both shared and modality-specific features are critical for characterizing cell states and supporting downstream analyses. Ideally, modality-specific features…
arXiv:2505.13230v2 Announce Type: replace-cross Abstract: Scaling laws in deep learning — empirical power-law relationships linking model performance to resource growth — have emerged as simple yet striking regularities across architectures, datasets, and tasks. These laws are particularly impactful in guiding…
arXiv:2509.21996v1 Announce Type: new Abstract: Hawkes process models are used in settings where past events increase the likelihood of future events occurring. Many applications record events as counts on a regular grid, yet discrete-time Hawkes models remain comparatively underused and…
arXiv:2508.02924v3 Announce Type: replace-cross Abstract: Transformer architectures dominate modern NLP but often demand heavy computational resources and intricate hyperparameter tuning. To mitigate these challenges, we propose a novel framework, BoostTransformer, that augments transformers with boosting principles through subgrid token selection…
arXiv:2509.22011v1 Announce Type: new Abstract: We present a rigorous asymptotic analysis of Echo State Networks (ESNs) in a teacher student setting with a linear teacher with oracle weights. Leveraging random matrix theory, we derive closed form expressions for the asymptotic…
arXiv:2509.22100v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have achieved remarkable success across a range of learning tasks. However, scaling GNNs to large graphs remains a significant challenge, especially for graph-level tasks. In this work, we introduce SHAKE-GNN, a…
