Search papers, labs, and topics across Lattice.
The University of Texas at Austin
2
0
3
Bayesian mixture-of-experts models can achieve robust density and parameter estimation with adaptive expert selection, fundamentally reshaping our approach to complex probabilistic modeling.
Self-distillation isn't just a trick: this paper proves it *provably* improves ridge regression performance, even with negative mixing weights in over-regularized regimes, and offers a one-shot tuning method to make it practical.
