A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
PRISM-FCP improves federated prediction robustness against Byzantine attacks.
Study optimizes shared singular subspace estimation from noisy matrices.
HCL learns shared and modality-specific latent representations for multimodal data.
The increased availability of the multi-view data (data on the same samples from multiple sources) has led to strong interest in models based on low-rank matrix factorizations. These models represent each data view via shared and individual components, and have been successfully applied for exploratory dimension reduct…
Model improves covariance estimation from shared and distinct datasets.
We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision. The setting is significant since tuple supervision is costly and sometimes eve…
We propose a GAN design which models multiple distributions effectively and discovers their commonalities and particularities. Each data distribution is modeled with a mixture of generator distributions. As the generators are partially shared between the modeling of different true data distributions, shared ones ca…
A new method for efficient online federated learning reduces communication overhead.
We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a subsequent one, due to the overwriting of shared parameters. To overcome this, w…
Sparse linear regression -- finding an unknown vector from linear measurements -- is now known to be possible with fewer samples than variables, via methods like the LASSO. We consider the multiple sparse linear regression problem, where several related vectors -- with partially shared support sets -- have to be recove…
Securely analyzes survival data across multiple institutions without revealing individual patient records.
New method for MTL with varying sparsity patterns across tasks.