Statistical Learning
Local policy search with Bayesian optimization Sarah Müller
Nevertheless, instead of systematically reasoning and actively choosing informative samples, policy gradients for local search are often obtained from random perturbations. These random samples yield high variance estimates and hence are sub-optimal in terms of sample complexity.
SGAM: Building a Virtual 3D World through Simultaneous Generation and Mapping
Our goal is to produce a realistic, globally consistent 3D world on a large scale.
Transformer Memory as a Differentiable Search Index Yi T ay, Vinh Q. Tran
Experiments demonstrate that given appropriate design choices, DSI significantly outperforms strong baselines such as dual encoder models.
Entropy-Driven Mixed-Precision Quantization for Deep Network Design: Appendix A Proof of Quantization Entropy Score A.1 Maximum Entropy
Rnnpool: efficient non-linear pooling for ram constrained inference.
Adapting to Function Difficulty and Growth Conditions in Private Optimization Hilal Asi Daniel Levy
We develop algorithms for private stochastic convex optimization that adapt to the hardness of the specific function we wish to optimize. While previous work provide worst-case bounds for arbitrary convex functions, it is often the case that the function at hand belongs to a smaller class that enjoys faster rates. Concretely, we show that for functions exhibiting κ-growth around the optimum, i.e., f ( x) f (x
Adapting to Function Difficulty and Growth Conditions in Private Optimization Hilal Asi Daniel Levy
We develop algorithms for private stochastic convex optimization that adapt to the hardness of the specific function we wish to optimize. While previous work provide worst-case bounds for arbitrary convex functions, it is often the case that the function at hand belongs to a smaller class that enjoys faster rates. Concretely, we show that for functions exhibiting κ-growth around the optimum, i.e., f ( x) f (x
