Associate Professor, Columbia University
2 papers at NeurIPS 2025
A multi-scale, multi-fidelity Bayesian Optimization (BO) approach where {data mixtures, model scale, training steps} are adaptively selected, achieving >2.6x speedups compared to multi-fidelity BO and random search baselines.
We investiage the use of autoregressive models for exchangeable sequences in decision-making, showing multi-step inference improves decision making and standard causal architectures outperform existing custom ones.
