sketching

This paper investigates distributed sketching for OLS regression, where sketches are built from partitioned subsets rather than the whole dataset, reducing computational cost. The authors characterize the exact excess loss of the averaged estimator and show it matches that of whole-data sketching when subset covariance divergence is small.

Introduces VISReg, a regularization method for JEPA (Joint Embedding Predictive Architecture) training that combines variance, invariance, and sketching constraints.

This paper derives a scaling law for sketched linear contrastive learning under a Gaussian latent-variable model, analyzing how risk decomposes into approximation, optimization, and statistical terms, and provides theoretical guidance for balancing model size, data, and compute in contrastive learning.

Inkwash is a WebGL2-based watercolor sketching app that simulates pigment flow and paper interaction, generated with Claude Fable 5. The article explains the technical pipeline of floating-point textures and shaders behind the realistic watercolor effect.

This paper introduces Bernstein–Schur kernels, a class of nonstationary kernels between shift-invariant and dot-product templates, and provides a random feature construction by sketching the finite modulation and randomizing the completely monotone radial factor. The method yields unbiased estimators with operator-norm bounds controlled by intrinsic dimensions, and experiments validate the approach on a biased kernel example.

This paper introduces a new differential privacy sketching mechanism based on fast transforms that achieves state-of-the-art privacy guarantees and improved runtime, and applies it to DP linear regression to obtain the first fast method for DP ordinary least squares.

Blokdots 3.0 is a product update for a hardware sketching tool, enabling users to sketch with hardware components.