Learning Graphical Models
The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition
When the losses are stochastically generated, [Simchowitz and Jamieson, 2019, Y ang et al., 2021]
The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition
When the losses are stochastically generated, [Simchowitz and Jamieson, 2019, Y ang et al., 2021]
Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning
We study risk-sensitive reinforcement learning (RL) based on the entropic risk measure. Although existing works have established non-asymptotic regret guarantees for this problem, they leave open an exponential gap between the upper and lower bounds. We identify the deficiencies in existing algorithms and their analysis that result in such a gap.
Multi-fidelity Monte Carlo: a pseudo-marginal approach
Prescott and Baker (2020) propose a multi-fidelity approach to ABC. In our work, the Russian roulette estimator is used to construct an unbiased, low-fidelity likelihood.
Nested Variational Inference
NVI learns proposals by optimizing a divergence at each level of nesting.
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
In many sequential decision making settings, the agent lacks complete information about the underlying state of the system, a phenomenon known as partial observability .
Across-animal odor decoding by probabilistic manifold alignment
When applied to recordings from the mouse olfactory bulb, our approach reveals low-dimensional population dynamics that are odor specific and have consistent structure across animals.
All your loss are belong to Bayes Christian Walder 1 2 Richard Nock
In this paper, we rely on a broader view of proper composite losses and a recent construct from information geometry, source functions, whose fitting alleviates constraints faced by canonical links.