Optimization
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs
Existing solutions either work under very specific assumptions or achieve bounds that are vacuous in some regimes.
GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference Ziang Li1, Mengda Y ang
To overcome these challenges, we propose a G AN-based LA tent S pace S earch attack ( GLASS) that harnesses abundant prior knowledge from public data using advanced StyleGAN technologies. Additionally, we introduce GLASS++ to enhance reconstruction stability.
Accelerating Value Iteration with Anchoring
In this paper, we present the first accelerated VI for both the Bellman consistency and optimality operators.
Accelerating Value Iteration with Anchoring Jongmin Lee 1 Ernest K. Ryu
In this paper, we present the first accelerated VI for both the Bellman consistency and optimality operators.
Online Learning under Adversarial Nonlinear Constraints
In many applications, learning systems are required to process continuous non-stationary data streams.