Search papers, labs, and topics across Lattice.
9 papers from Google DeepMind on Training Efficiency & Optimization
Dynamic quantization, a widely adopted optimization for efficient ML serving, can leak your data to adversaries sharing the same batch.
Generative AI evaluation can be sped up by 8-65x without sacrificing accuracy by proactively focusing on the most informative test cases using a pre-trained Gaussian Process surrogate model.
DPP-based Monte Carlo integration can offer variance reduction, but choosing the right DPP鈥攆ixed vs. tailored to the integrand鈥攄etermines whether you get a biased but faster converging estimator or an unbiased but standard-rate estimator.
Entropy regularization makes planning provably easy: SmoothCruiser achieves polynomial sample complexity in MDPs where standard methods fail.
Forget sub-Gaussian assumptions: this semi-bandit algorithm adapts to the true covariance structure of outcomes, leading to tighter regret bounds and better performance.
Refining generative models with discriminator guidance provably improves generalization, offering a theoretical justification for techniques like score-based diffusion.
Unlock asymptotically normal and semiparametrically efficient estimators in adaptive data collection by using a novel target-specific condition called "directional stability," which is weaker than previous target-agnostic conditions.
Robots can now learn long-horizon tasks far more effectively by distilling complex histories into a few key visual moments, outperforming standard imitation learning by 70% on real-world tasks.
Ditch reward models: Nash Mirror Prox achieves fast, stable convergence to a Nash equilibrium directly from human preferences, sidestepping the limitations of traditional RLHF.
