Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution given its unnormalized density function. This algorithm relies on a sequence of interpolating distributions bridging the target to an initial tractable distribution such as the well-known geometric mean path of unnormalized distributions which is assumed to be suboptimal in general. In this paper, we prove that the geometric annealing corresponds to the distribution path that minimizes the KL divergence between the current particle distribution and the desired target when the feasible change in the particle distribution is constrained. Following this observation, we derive the constant rate discretization schedule for this annealing sequence, which adjusts the schedule to the difficulty of moving samples between the initial and the target distributions. We further extend our results to $f$-divergences and present the respective dynamics of annealing sequences based on which we propose the Constant Rate AIS (CR-AIS) algorithm and its efficient implementation for $\alpha$-divergences. We empirically show that CR-AIS performs well on multiple benchmark distributions while avoiding the computationally expensive tuning loop in existing Adaptive AIS.

We propose a novel algorithm for data augmentation in nonlinear over-parametrized regression. Our data augmentation algorithm borrows from the literature on causality. Contrary to the current state-of-the-art solutions that rely on modifications of Mixup algorithm, we extend the recently proposed distributionally robust Anchor regression (AR) method for data augmentation. Our Anchor Data Augmentation (ADA) uses several replicas of the modified samples in AR to provide more training examples, leading to more robust regression predictions. We apply ADA to linear and nonlinear regression problems using neural networks. ADA is competitive with state-of-the-art C-Mixup solutions.

Abstract Annealed Importance Sampling (AIS) is a popular algorithm used to estimates the intractable marginal likelihood of deep generative models. Although AIS is guaranteed to provide unbiased estimate for any set of hyperparameters, the common implementations rely on simple heuristics such as the geometric average bridging distributions between initial and the target distribution which affect the estimation performance when the computation budget is limited. In order to reduce the number of sampling iterations, we present a parameteric AIS process with flexible intermediary distributions defined by a residual density with respect to the geometric mean path. Our method allows parameter sharing between annealing distributions, the use of fix linear schedule for discretization and amortization of hyperparameter selection in latent variable models. We assess the performance of Optimized-Path AIS for marginal likelihood estimation of deep generative models and compare it to compare it to more computationally intensive AIS.

In this paper, we propose a new packet prioritization scheme in order to exploit the full-duplex (FD) capability of the access point (AP) more efficiently, in an asymmetric IEEE 802.11-based WLAN, i.e., only the AP has the in-band FD communications capability. In this respect, we consider a modified version of IEEE 802.11 MAC protocol such that at any transmission opportunity in which AP has the role of the transmitter or the receiver, it does the best to select a partner packet to be simultaneously received or transmitted, respectively. The key feature of our proposed partner packet selection scheme is to reduce the idle time intervals that in an FD transmission opportunity, due to different transmission times of the packet and its partner usually exist. To this end, we consider the packet lengths, the waiting time of the packets as well as the interfering effects of the two simultaneously active links on each other as the effective factors in prioritizing the packets to be selected as the partner. We map the problem onto finding a two-sided stable many-to-many matching table. Our numerical results indicate the high efficiency of the proposed scheme in exploiting the time, i.e., decreasing idle time intervals as well as increasing the throughput at the cost of controlled relaxation of the average delay.