Web-scale repositories of products, patents and scientific papers offer an opportunity for creating automated systems that scour millions of ideas and assist users in discovering inspirations and solutions. Yet the common representation of ideas is in the form of raw textual descriptions, lacking important structure that is required for supporting creative innovation. Prior work has pointed to the importance of functional structure -- capturing the mechanisms and purposes of inventions -- for allowing users to discover structural connections across ideas and creatively adapt existing technologies. However, the use of functional representations was either coarse and limited in expressivity, or dependent on curated knowledge bases with poor coverage and significant manual effort from users. To help bridge this gap and unlock the potential of large-scale idea mining, we propose a novel computational representation that automatically breaks up products into fine-grained functional facets. We train a model to extract these facets from a challenging real-world corpus of invention descriptions, and represent each product as a set of facet embeddings. We design similarity metrics that support granular matching between functional facets across ideas, and use them to build a novel functional search capability that enables expressive queries for mechanisms and purposes. We construct a graph capturing hierarchical relations between purposes and mechanisms across an entire corpus of products, and use the graph to help problem-solvers explore the design space around a focal problem and view related problem perspectives. In empirical user studies, our approach leads to a significant boost in search accuracy and in the quality of creative inspirations, outperforming strong baselines and state-of-art representations of product texts by 50-60%.

We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement learning. Unlike previous work, our framework is able to prove theorems both end-to-end and from scratch (i.e., without relying on example proofs from human experts). We formulate the process of ITP as a Markov decision process (MDP) in which each state represents a set of potential derivation paths. The agent learns to select promising derivations as well as appropriate tactics within each derivation using deep policy gradients. This structure allows us to introduce a novel backtracking mechanism which enables the agent to efficiently discard (predicted) dead-end derivations and restart the derivation from promising alternatives. Experimental results show that the framework provides comparable performance to that of the approaches that use human experts, and that it is also capable of proving theorems that it has never seen during training. We further elaborate the role of each component of the framework using ablation studies.

Robotic fabric manipulation has applications in home robotics, textiles, senior care and surgery. Existing fabric manipulation techniques, however, are designed for specific tasks, making it difficult to generalize across different but related tasks. We build upon the Visual Foresight framework to learn fabric dynamics that can be efficiently reused to accomplish different sequential fabric manipulation tasks with a single goal-conditioned policy. We extend our earlier work on VisuoSpatial Foresight (VSF), which learns visual dynamics on domain randomized RGB images and depth maps simultaneously and completely in simulation. In this earlier work, we evaluated VSF on multi-step fabric smoothing and folding tasks against 5 baseline methods in simulation and on the da Vinci Research Kit (dVRK) surgical robot without any demonstrations at train or test time. A key finding was that depth sensing significantly improves performance: RGBD data yields an 80% improvement in fabric folding success rate in simulation over pure RGB data. In this work, we vary 4 components of VSF, including data generation, the choice of visual dynamics model, cost function, and optimization procedure. Results suggest that training visual dynamics models using longer, corner-based actions can improve the efficiency of fabric folding by 76% and enable a physical sequential fabric folding task that VSF could not previously perform with 90% reliability. Code, data, videos, and supplementary material are available at https://sites.google.com/view/fabric-vsf/.

Vehicle Re-identification (re-id) over surveillance camera network with non-overlapping field of view is an exciting and challenging task in intelligent transportation systems (ITS). Due to its versatile applicability in metropolitan cities, it gained significant attention. Vehicle re-id matches targeted vehicle over non-overlapping views in multiple camera network. However, it becomes more difficult due to inter-class similarity, intra-class variability, viewpoint changes, and spatio-temporal uncertainty. In order to draw a detailed picture of vehicle re-id research, this paper gives a comprehensive description of the various vehicle re-id technologies, applicability, datasets, and a brief comparison of different methodologies. Our paper specifically focuses on vision-based vehicle re-id approaches, including vehicle appearance, license plate, and spatio-temporal characteristics. In addition, we explore the main challenges as well as a variety of applications in different domains. Lastly, a detailed comparison of current state-of-the-art methods performances over VeRi-776 and VehicleID datasets is summarized with future directions. We aim to facilitate future research by reviewing the work being done on vehicle re-id till to date.

Last month, I shared a short list of dataset repositories that I planned to recommend to students as inspiration for their class projects. Thanks to all the great suggestions via the Twitter thread above, this list has grown quite a bit! Now, with the semester being in full swing, I recently shared this set of dataset repositories with my deep learning class. However, beyond using this list to find inspiration for interesting student class projects, these are also good places to look for additional benchmark datasets for your model, so I am putting it out here, hoping you find it useful! It is hard to sort by priority or to pick favorites, so the following list is sorted alphabetically.

Recent studies revealed the mathematical connection of deep neural network (DNN) and dynamic system. However, the fundamental principle of DNN has not been fully characterized with dynamic system in terms of optimization and generalization. To this end, we build the connection of DNN and continuity equation where the measure is conserved to model the forward propagation process of DNN which has not been addressed before. DNN learns the transformation of the input distribution to the output one. However, in the measure space, there are infinite curves connecting two distributions. Which one can lead to good optimization and generaliztion for DNN? By diving the optimal transport theory, we find DNN with weight decay attempts to learn the geodesic curve in the Wasserstein space, which is induced by the optimal transport map. Compared with plain network, ResNet is a better approximation to the geodesic curve, which explains why ResNet can be optimized and generalize better. Numerical experiments show that the data tracks of both plain network and ResNet tend to be line-shape in term of line-shape score (LSS), and the map learned by ResNet is closer to the optimal transport map in term of optimal transport score (OTS). In a word, we conclude a mathematical principle of deep learning is to learn the geodesic curve in the Wasserstein space; and deep learning is a great engineering realization of continuous transformation in high-dimensional space.

During the past few years, there has been considerable success of applying deep learning to complex problems ranging from speech synthesis (cite WaveNet) to deep reinforcement learning achieving victories in complex games such as Go [19]. This, in turn, has fueled massive interest in the field. At the core of deep learning are training algorithms which allow neural networks to learn from the data they are presented or learn how to extremize a target quantity. One such algorithm is the stochastic gradient descent (SGD) (cite) and it is one of most widely used training algorithms. However, this does not come without issues as many training algorithms suffer from being slow at converging to the optimal state and lack stability when approaching the optimum (citation needed).One common approach is to transform the data into a manageable form through centring and scaling the data and it is the base of many normalization techniques. In fact, the success of "Batch Normalization" by Sgzedy and Ioffe [8] sparked an interest in such techniques. In [8], they noticed that the learning procedure, which uses stochastic gradient descent (SGD), or derived adaptive algorithms like Adam [12], can be hindered and they claimed that a phenomenon known as internal covariance shift is the cause. This phenomenon depends on the change of the network's weights during backpropagation that can lead to the shift of data-distribution towards the saturation regime of the activation

It has been empirically observed that, in deep neural networks, the solutions found by stochastic gradient descent from different random initializations can be often connected by a path with low loss. Recent works have shed light on this intriguing phenomenon by assuming either the over-parameterization of the network or the dropout stability of the solutions. In this paper, we reconcile these two views and present a novel condition for ensuring the connectivity of two arbitrary points in parameter space. This condition is provably milder than dropout stability, and it provides a connection between the problem of finding low-loss paths and the memorization capacity of neural nets. This last point brings about a trade-off between the quality of features at each layer and the over-parameterization of the network. As an extreme example of this trade-off, we show that (i) if subsets of features at each layer are linearly separable, then almost no over-parameterization is needed, and (ii) under generic assumptions on the features at each layer, it suffices that the last two hidden layers have $\Omega(\sqrt{N})$ neurons, $N$ being the number of samples. Finally, we provide experimental evidence demonstrating that the presented condition is satisfied in practical settings even when dropout stability does not hold.

Nowadays, combinatorial optimization (CO) is an interdisciplinary field spanning optimization, operations research, discrete mathematics, and computer science, with many critical real-world applications such as vehicle routing or scheduling; see [71] for a general overview. Intuitively, CO deals with selecting a subset from a finite set that optimizes a cost or objective function. Although many CO problems are hard from a complexity theory standpoint due to their discrete nature, many of them are routinely solved in practice. Historically, the optimization and theoretical computer science communities have been focusing on finding optimal [71], heuristic [12], or approximative [130] solutions for individual problem instances. However, in many practical situations of interest, one often needs to solve problem instances which share patterns and characteristics repeatedly.

Minimax optimization has recently gained a lot of attention as adversarial architectures and algorithms proliferate. Often, smooth minimax games proceed by simultaneous or alternating gradient updates. Although algorithms with alternating updates are commonly used in practice for many applications (e.g., GAN training), the majority of existing theoretical analyses focus on simultaneous algorithms. In this paper, we study alternating gradient descent-ascent (Alt-GDA) in minimax games and show that Alt-GDA is superior to its simultaneous counterpart (Sim-GDA) in many settings. In particular, we prove that Alt-GDA achieves a near-optimal local convergence rate for strongly-convex strongly-concave problems while Sim-GDA converges with a much slower rate. Moreover, we show that the acceleration effect of alternating updates remains when the minimax problem has only strong concavity in the dual variables. Numerical experiments on quadratic minimax games validate our claims. Additionally, we demonstrate that alternating updates speed up GAN training significantly and the use of optimism only helps for simultaneous algorithms.