Xiaoyu Jiang

Mengdi Wu, Xiaoyu Jiang, Oded Padon et al.

This paper presents Prism, the first symbolic superoptimizer for tensor programs. The key idea is sGraph, a symbolic, hierarchical representation that compactly encodes large classes of tensor programs by symbolically representing some execution parameters. Prism organizes optimization as a two-level search: it constructs symbolic graphs that represent families of programs, and then instantiates them into concrete implementations. This formulation enables structured pruning of provably suboptimal regions of the search space using symbolic reasoning over operator semantics, algebraic identities, and hardware constraints. We develop techniques for efficient symbolic graph generation, equivalence verification via e-graph rewriting, and parameter instantiation through auto-tuning. Together, these components allow Prism to bridge the rigor of exhaustive search with the scalability required for modern ML workloads. Evaluation on five commonly used LLM workloads shows that Prism achieves up to $2.2\times$ speedup over best superoptimizers and $4.9\times$ over best compiler-based approaches, while reducing end-to-end optimization time by up to $3.4\times$.

Xiaoyu Jiang, Sokratia Georgaka, Magnus Rattray et al.

The Multi-Output Gaussian Process is is a popular tool for modelling data from multiple sources. A typical choice to build a covariance function for a MOGP is the Linear Model of Coregionalization (LMC) which parametrically models the covariance between outputs. The Latent Variable MOGP (LV-MOGP) generalises this idea by modelling the covariance between outputs using a kernel applied to latent variables, one per output, leading to a flexible MOGP model that allows efficient generalization to new outputs with few data points. Computational complexity in LV-MOGP grows linearly with the number of outputs, which makes it unsuitable for problems with a large number of outputs. In this paper, we propose a stochastic variational inference approach for the LV-MOGP that allows mini-batches for both inputs and outputs, making computational complexity per training iteration independent of the number of outputs.