Eric Huang

UAI Conference 2025 Conference Paper

Tuning Algorithmic and Architectural Hyperparameters in Graph-Based Semi-Supervised Learning with Provable Guarantees

• Ally Yalei Du
• Eric Huang
• Dravyansh Sharma

Graph-based semi-supervised learning is a powerful paradigm in machine learning for modeling and exploiting the underlying graph structure that captures the relationship between labeled and unlabeled data. A large number of classical as well as modern deep learning based algorithms have been proposed for this problem, often having tunable hyperparameters. We initiate a formal study of tuning algorithm hyperparameters from parameterized algorithm families for this problem. We obtain novel $O(\log n)$ pseudo-dimension upper bounds for hyperparameter selection in three classical label propagation-based algorithm families, where $n$ is the number of nodes, implying bounds on the amount of data needed for learning provably good parameters. We further provide matching $\Omega(\log n)$ pseudo-dimension lower bounds, thus asymptotically characterizing the learning-theoretic complexity of the parameter tuning problem. We extend our study to selecting architectural hyperparameters in modern graph neural networks. We bound the Rademacher complexity for tuning the self-loop weighting in recently proposed Simplified Graph Convolution (SGC) networks. We further propose a tunable architecture that interpolates graph convolutional neural networks (GCN) and graph attention networks (GAT) in every layer, and provide Rademacher complexity bounds for tuning the interpolation coefficient.

ICRA Conference 2022 Conference Paper

Contact Mode Guided Motion Planning for Quasidynamic Dexterous Manipulation in 3D

• Xianyi Cheng
• Eric Huang
• Yifan Hou
• Matthew T. Mason

This paper presents Contact Mode Guided Manipulation Planning (CMGMP) for 3D quasistatic and quasi-dynamic rigid body motion planning in dexterous manipulation. The CMGMP algorithm generates hybrid motion plans including both continuous state transitions and discrete contact mode switches, without the need for pre-specified contact sequences or pre-designed motion primitives. The key idea is to use automatically enumerated contact modes of environment-object contacts to guide the tree expansions during the search. Contact modes automatically synthesize manipulation primitives, while the sampling-based planning framework sequences those primitives into a coherent plan. We test our algorithm on fourteen 3D manipulation tasks, and validate our models by executing some plans open-loop on a real robot-manipulator system 1 1 The video is available at https://youtu.be/JuLlliG3vGc.

ICRA Conference 2021 Conference Paper

Contact Mode Guided Sampling-Based Planning for Quasistatic Dexterous Manipulation in 2D

• Xianyi Cheng
• Eric Huang
• Yifan Hou
• Matthew T. Mason

The discontinuities and multi-modality introduced by contacts make manipulation planning challenging. Many previous works avoid this problem by pre-designing a set of high-level motion primitives like grasping and pushing. However, such motion primitives are often not adequate to describe dexterous manipulation motions. In this work, we propose a method for dexterous manipulation planning at a more primitive level. The key idea is to use contact modes to guide the search in a sampling-based planning framework. Our method can automatically generate contact transitions and motion trajectories under the quasistatic assumption. In the experiments, this method sometimes generates motions that are often pre-designed as motion primitives, as well as dexterous motions that are more task-specific 1.

ICRA Conference 2019 Conference Paper

Large-Scale Multi-Object Rearrangement

• Eric Huang
• Zhenzhong Jia
• Matthew T. Mason

This paper describes a new robotic tabletop rearrangement system, and presents experimental results. The tasks involve rearranging as many as 30 to 100 blocks, sometimes packed with a density of up to 40%. The high packing factor forces the system to push several objects at a time, making accurate simulation difficult, if not impossible. Nonetheless, the system achieves goals specifying the pose of every object, with an average precision of ± 1 mm and ± 2°. The system searches through policy rollouts of simulated pushing actions, using an Iterated Local Search technique to escape local minima. In real world execution, the system executes just one action from a policy, then uses a vision system to update the estimated task state, and replans. The system accepts a fully general description of task goals, which means it can solve the singulation and separation problems addressed in prior work, but can also solve sorting problems and spell out words, among other things. The paper includes examples of several solved problems, statistical analysis of the system's behavior on different types of problems, and some discussion of limitations, insights, and future work.

ICRA Conference 2017 Conference Paper

Motion planning with graph-based trajectories and Gaussian process inference

• Eric Huang
• Mustafa Mukadam
• Zhen Liu
• Byron Boots

Motion planning as trajectory optimization requires generating trajectories that minimize a desired objective function or performance metric. Finding a globally optimal solution is often intractable in practice: despite the existence of fast motion planning algorithms, most are prone to local minima, which may require re-solving the problem multiple times with different initializations. In this work we provide a novel motion planning algorithm, GPMP-GRAPH, that considers a graph-based initialization that simultaneously explores multiple homotopy classes, helping to contend with the local minima problem. Drawing on previous work to represent continuous-time trajectories as samples from a Gaussian process (GP) and formulating the motion planning problem as inference on a factor graph, we construct a graph of interconnected states such that each path through the graph is a valid trajectory and efficient inference can be performed on the collective factor graph. We perform a variety of benchmarks and show that our approach allows the evaluation of an exponential number of trajectories within a fraction of the computational time required to evaluate them one at a time, yielding a more thorough exploration of the solution space and a higher success rate.

NeurIPS Conference 2011 Conference Paper

Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection

• Richard Socher
• Eric Huang
• Jeffrey Pennin
• Christopher Manning
• Andrew Ng

Paraphrase detection is the task of examining two sentences and determining whether they have the same meaning. In order to obtain high accuracy on this task, thorough syntactic and semantic analysis of the two statements is needed. We introduce a method for paraphrase detection based on recursive autoencoders (RAE). Our unsupervised RAEs are based on a novel unfolding objective and learn feature vectors for phrases in syntactic trees. These features are used to measure the word- and phrase-wise similarity between two sentences. Since sentences may be of arbitrary length, the resulting matrix of similarity measures is of variable size. We introduce a novel dynamic pooling layer which computes a fixed-sized representation from the variable-sized matrices. The pooled representation is then used as input to a classifier. Our method outperforms other state-of-the-art approaches on the challenging MSRP paraphrase corpus.

AAAI Conference 2011 Conference Paper

Optimal Packing of High-Precision Rectangles

• Eric Huang
• Richard Korf

The rectangle-packing problem consists of finding an enclosing rectangle of smallest area that can contain a given set of rectangles without overlap. Our new benchmark includes rectangles of successively higher precision, challenging the previous state-of-the-art, which enumerates all locations for placing rectangles, as well as all bounding box widths and heights up to the optimal box. We instead limit the rectangles’ coordinates and bounding box dimensions to the set of subset sums of the rectangles’ dimensions. We also dynamically prune values by learning from infeasible subtrees and constrain the problem by replacing rectangles and empty space with larger rectangles. Compared to the previous state-of-the-art, we test 4, 500 times fewer bounding boxes on the high-precision benchmark and solve N=9 over two orders of magnitude faster. We also present all optimal solutions up to N=15, which requires 39 bits of precision to solve. Finally, on the open problem of whether or not one can pack a particular infinite series of rectangles into the unit square, we pack the first 50, 000 such rectangles with a greedy heuristic and conjecture that the entire infinite series can fit. Our open source solver is available at http: //code. google. com/p/rectpack.

SoCS Conference 2011 Conference Paper

Optimal Packing of High-Precision Rectangles

• Eric Huang
• Richard E. Korf

The rectangle-packing problem consists of finding an enclosing rectangle of smallest area that can contain a given set of rectangles without overlap. Our new benchmark includes rectangles of successively higher precision, a problem for the previous state-of-the-art, which enumerates all locations for placing rectangles. We instead limit these locations and bounding box dimensions to the set of subset sums of the rectangles

AAAI Conference 2010 Conference Paper

Optimal Rectangle Packing on Non-Square Benchmarks

• Eric Huang
• Richard Korf

The rectangle packing problem consists of finding an enclosing rectangle of smallest area that can contain a given set of rectangles without overlap. We propose two new benchmarks, one where the orientation of the rectangles is fixed and one where it is free, that include rectangles of various aspect ratios. The new benchmarks avoid certain properties of easy instances, which we identify as instances where rectangles have dimensions in common or where a few rectangles occupy most of the area. Our benchmarks are much more difficult for the previous state-of-the-art solver, requiring orders of magnitude more time, compared to similar-sized instances from a popular benchmark consisting only of squares. On the new benchmarks, we improve upon the previous strategy used to handle dominance conditions, we define a variable order over non-square rectangles that generalizes previous strategies, and we present a way to adjust the sizes of intervals of values for each rectangle’s x-coordinates. Using these techniques together, we can solve the new oriented benchmark about 500 times faster, and the new unoriented benchmark about 40 times faster than the previous state-of-the-art.

IJCAI Conference 2009 Conference Paper

• Eric Huang
• Richard E. Korf

The rectangle packing problem consists of finding an enclosing rectangle of smallest area that can contain a given set of rectangles without overlap. Our algorithm picks the x-coordinates of all the rectangles before picking any of the y-coordinates. For the x-coordinates, we present a dynamic variable ordering heuristic and an adaptation of a pruning algorithm used in previous solvers. We then transform the rectangle packing problem into a perfect packing problem that has no empty space, and present inference rules to reduce the instance size. For the y-coordinates we search a space that models empty positions as variables and rectangles as values. Our solver is over 19 times faster than the previous state-of-the-art on the largest problem solved to date, allowing us to extend the known solutions for a consecutive-square packing benchmark from N=27 to N=32.

ICRA Conference 1999 Conference Paper

Development of a Collaborative and Event-Driven Supply Chain Information System Using Mobile Object Technolog

• Eric Huang
• Fan-Tien Cheng
• Haw Ching Yang

Information integration of the supply chain for the manufacturing industry is essential because a competent and promising company needs an efficient information system to communicate with its customers, supplies, and partners within the entire supply chain. In this research, a collaborative and event-driven supply chain information system (SCIS) is developed by using mobile object technology. The Unified Modeling Language (UML) is applied to analyze and design the SCIS Framework which contains two major components: information coordinator component (ICC) and agent component (AC). The ICC acts as the information integration manager. It manages all the ACs and establishes proper event channels for them to exchange information. Each member within the supply chain needs to possess an AC such that it can utilize the SCIS to exchange information with the other members. An application example is constructed and its corresponding system integration and testing procedure is demonstrated. From this demonstration result, it is believed that this SCIS framework provides a collaborative, event-driven, object-oriented, and agent-based infrastructure for the supply chain members to mutually exchange information efficiently.