Lead Author Spotlight | NeurIPS 2021

Brain activities are often complex and noisy, yet it is believed by neuroscientists that a low-dimensional neural representation that governs neural signals exists. The biggest motivation of this project is to find a low-dimensional representation space that could ‘explain’ the neural signals. Our work SwapVAE presents an initial step towards this goal by combining self-supervised learning (SSL) techniques with the generative modeling framework to learn interpretable representations of neural activities.

It should be our latent space augmentation operation BlockSwap. BlockSwap makes the latent representation more interpretable by separating the latent representation into augmentation-invariant information and augmentation-variant information, and swapping the invariant part before reconstruction. We hope BlockSwap can be applied in other scenarios when interpretability matters.

My lesson was summarized 2000 years ago by Aristotle: “For the things we have to learn before we can do them, we learn by doing them.”

I am excited to check out other cutting-edge works! I hope to learn from the computational neuroscientists to see how they approach similar problems, and am also excited to learn from other deep learning scientists for inspiration.

Despite that the adjoint-based optimization process of Neural ODEs is originated from Optimal Control Principle, few attempts have been made along this principle. We are interested in seeing the practical improvements it can bring to the table.

That the deep learning optimization is fundamentally intertwined with optimal control principle paves an elegant path towards principled training improvement and new applications that will otherwise remain unexplored in the current framework.

Math won’t lie 🙂

I am definitely excited to learn more at NeurIPS.

I was motivated to work on this paper to accelerate embodied AI towards being able to complete realistic tasks in the home such as cooking meals, loading the dishwasher, or cleaning up. Previously, working towards this goal was challenging due to the lack of datasets, slow simulators, and missing benchmarks to measure progress. Motivated by these three deficiencies, our work proposed a dataset of interactive house-scale scenes, a simulator that is 100x faster than prior work, and a benchmark for realistic tasks in the home.

One takeaway is that Habitat 2.0 is the perfect test bed for developing agents in interactive, 3D, and physics-enabled tasks in the home. Also that researchers should get started using the dataset, simulator, and benchmark at https://aihabitat.org.

A part of the project was benchmarking how prior approaches performed on long and complex tasks in the home such as preparing groceries or setting the table. An “aha” moment was realizing that all previous methods achieved zero success on the hardest version of the benchmark. This finding informs my future research in learning algorithms that address such long and compositional task structures.

I am excited to meet other researchers in the space. I hope to take away new connections from the experience.

In this work, we bridge discrete and continuous optimization insights to eliminate projections bottlenecks appearing within optimal optimization algorithms such as mirror descent.

This has to be to always keep the big picture and practical impact of your work in mind. Also, that submitting to NeurIPS is a goal that should always be in your mind while doing the research and not after the research is done; this allows you to adapt the work to the “NeurIPS way” as you go along.

I am really excited to see the latest cutting-edge research, and hope to network and make as many connections as I can.

We wanted to come up with a simple 5-line optimization algorithm that would achieve the same convergence guarantees as more complex algorithms in the literature for minimizing generalized self-concordant functions in the projection-free case.

The main takeaway is that simple algorithms are usually more robust than more complex algorithms, and in some special cases they can achieve similar convergence properties!

When we were scouting the literature we realized that a lot of the algorithms for minimizing this class of functions were complex, they utilized expensive operations, and they achieved sublinear convergence. We realized that with a few simple tricks, and with much cheaper operations we could theoretically prove the same properties, while being computationally cheaper to run.

I’m excited to meet other researchers working on similar topics, and I’m sure that new and interesting ideas will spring from these interactions at the conference.

Recent literature obtains finite sample guarantees for discounted-reward TD learning and Q-learning algorithms. Such a study of average-reward RL algorithms is not undertaken, which are known to be more challenging to study than their discounted-reward counterparts.

One takeaway: We establish the first finite sample convergence guarantees of average-reward TD learning with linear function approximation and average-reward tabular Q-learning in the literature.
Reason: The theoretical understanding of average-reward RL methods is quite limited.

We realized that our approach is simple and general, so we expect it to have broader applications in other problems.

It is a great opportunity to learn the state-of-the-art research on various machine learning problems. I hope to find some research ideas for my future work.

Given my prior work in interpretable machine learning, I was interested in identifying the utility of explainable AI (xAI) approaches when deployed to complex, human-machine teaming domains. Furthermore, I was hoping that deploying several xAI approaches within a human-machine teaming setting would reveal key drawbacks in the real-world practicability of current xAI approaches and inspire my future work in developing xAI for high-performance human-machine teaming.

Full explainability, providing complete information about a collaborative robot’s policy, is preferred by users prior to task execution. However during task execution, partial explainability, which provides a low-level abstraction of the collaborative robot’s policy, proves more beneficial.

We hope this takeaway can inform other researchers in their design of xAI approaches, modifying the design appropriately based on whether the approach is online (during task execution) or offline (before or after task execution).

When running human-subjects studies, assess/plot your data often. You may detect new and thought-provoking patterns that can further inform your experimental analysis and lead to interesting conclusions.

I’m excited to present my research and hope to both meet other researchers in the field and discover interesting future directions.