Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Affiliation:
3
0
0
2
Halving oracle calls in momentum methods can slash training loss by up to 43% without sacrificing convergence.
A novel multi-objective optimizer achieves $O(T^{-1/4})$ convergence with stochastic gradients, independent of task count, by integrating norm-constrained oracles and entropic weight updates.
A new optimization framework, PISO, achieves state-of-the-art function-evaluation complexities for partially informed gradients by cleverly tracking and centering on the unknown residual.