Author name cluster

Jerry Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

SD-KDE: Score-Debiased Kernel Density Estimation

Elliot Epstein
Rajat Vadiraj Dwaraknath
Thanawat Sornwanee
John Winnicki
Jerry Liu

We propose a method for density estimation that leverages an estimated score function to debias kernel density estimation (SD-KDE). In our approach, each data point is adjusted by taking a single step along the score function with a specific choice of step size, followed by standard KDE with a modified bandwidth. The step size and modified bandwidth are chosen to remove the leading order bias in the KDE, improving the asymptotic convergence rate. Our experiments on synthetic tasks in 1D, 2D and on MNIST, demonstrate that our proposed SD-KDE method significantly reduces the mean integrated squared error compared to the standard Silverman KDE, even with noisy estimates in the score function. These results underscore the potential of integrating score-based corrections into nonparametric density estimation.

PDF Details

ICRA Conference 2021 Conference Paper

Deep Structured Reactive Planning

Jerry Liu
Wenyuan Zeng
Raquel Urtasun
Ersin Yumer

An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the surrounding scene. This requires jointly reasoning about the behavior of other actors while deciding its own actions as these two processes are inherently intertwined – a vehicle will yield to us if we decide to proceed first at the intersection but will proceed first if we decide to yield. However, this is not captured in most self-driving pipelines, where planning follows prediction. In this paper we propose a novel data-driven, reactive planning objective which allows a self-driving vehicle to jointly reason about its own plans as well as how other actors will react to them. We formulate the problem as an energy-based deep structured model that is learned from observational data and encodes both the planning and prediction problems. Through simulations based on both real-world driving and synthetically generated dense traffic, we demonstrate that our reactive model outperforms a non-reactive variant in successfully completing highly complex maneuvers (lane merges/turns in traffic) faster, without trading off collision rate. Please see our supplementary document https://tinyurl.com/3nukpn5b for all additional details.

Details

NeurIPS Conference 2020 Conference Paper

MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models

Sourav Biswas
Jerry Liu
Kelvin Wong
Shenlong Wang
Raquel Urtasun

We present a novel compression algorithm for reducing the storage of LiDAR sensory data streams. Our model exploits spatio-temporal relationships across multiple LIDAR sweeps to reduce the bitrate of both geometry and intensity values. Towards this goal, we propose a novel conditional entropy model that models the probabilities of the octree symbols, by considering both coarse level geometry and previous sweeps’ geometric and intensity information. We then exploit the learned probability to encode the full data-stream into a compact one. Our experiments demonstrate that our method significantly reduces the joint geometry and intensity bitrate over prior state-of-the-art LiDAR compression methods, with a reduction of 7–17% and 15–35% on the UrbanCity and SemanticKITTI datasets respectively.

PDF Details

AIJ Journal 2011 Journal Article

From Bidirectional Associative Memory to a noise-tolerant, robust Protein Processor Associative Memory

Omer Qadir
Jerry Liu
Gianluca Tempesti
Jon Timmis
Andy Tyrrell

Protein Processor Associative Memory (PPAM) is a novel architecture for learning associations incrementally and online and performing fast, reliable, scalable hetero-associative recall. This paper presents a comparison of the PPAM with the Bidirectional Associative Memory (BAM), both with Kosko's original training algorithm and also with the more popular Pseudo-Relaxation Learning Algorithm for BAM (PRLAB). It also compares the PPAM with a more recent associative memory architecture called SOIAM. Results of training for object-avoidance are presented from simulations using player/stage and are verified by actual implementations on the E-Puck mobile robot. Finally, we show how the PPAM is capable of achieving an increase in performance without using the typical weighted-sum arithmetic operations or indeed any arithmetic operations.

Details DOI