Search papers, labs, and topics across Lattice.
University of Sydney
4
0
6
Closing the gap in multiclass PAC learning reveals that optimal excess risk can be achieved without prior knowledge of oracle risk, fundamentally shifting our understanding of classifier performance.
The traditional complexity of leverage-score algorithms is misleading; the real challenge lies in identification, not accuracy, allowing for a dramatic reduction in query complexity.
Differential privacy in language tasks is surprisingly cheap: approximate DP is free, and pure DP only reduces performance by a factor of $\min\{1,\varepsilon\}$.
By intelligently fusing Wiener Chaos Expansion with Neural Operators, this new method cracks the notoriously difficult problem of simulating singular stochastic PDEs without relying on computationally expensive renormalization techniques.
