Paper Group ANR 242
Survey Bandits with Regret Guarantees. FoCL: Feature-Oriented Continual Learning for Generative Models. Revisiting Spatial Invariance with Low-Rank Local Connectivity. Utilizing Language Relatedness to improve Machine Translation: A Case Study on Languages of the Indian Subcontinent. Metaplasticity in Multistate Memristor Synaptic Networks. Using H …
Survey Bandits with Regret Guarantees
| Title | Survey Bandits with Regret Guarantees |
| Authors | Sanath Kumar Krishnamurthy, Susan Athey |
| Abstract | We consider a variant of the contextual bandit problem. In standard contextual bandits, when a user arrives we get the user’s complete feature vector and then assign a treatment (arm) to that user. In a number of applications (like healthcare), collecting features from users can be costly. To address this issue, we propose algorithms that avoid needless feature collection while maintaining strong regret guarantees. |
| Tasks | Multi-Armed Bandits |
| Published | 2020-02-23 |
| URL | https://arxiv.org/abs/2002.09814v1 |
| https://arxiv.org/pdf/2002.09814v1.pdf | |
| PWC | https://paperswithcode.com/paper/survey-bandits-with-regret-guarantees |
| Repo | |
| Framework | |
FoCL: Feature-Oriented Continual Learning for Generative Models
| Title | FoCL: Feature-Oriented Continual Learning for Generative Models |
| Authors | Qicheng Lao, Mehrzad Mortazavi, Marzieh Tahaei, Francis Dutil, Thomas Fevens, Mohammad Havaei |
| Abstract | In this paper, we propose a general framework in continual learning for generative models: Feature-oriented Continual Learning (FoCL). Unlike previous works that aim to solve the catastrophic forgetting problem by introducing regularization in the parameter space or image space, FoCL imposes regularization in the feature space. We show in our experiments that FoCL has faster adaptation to distributional changes in sequentially arriving tasks, and achieves the state-of-the-art performance for generative models in task incremental learning. We discuss choices of combined regularization spaces towards different use case scenarios for boosted performance, e.g., tasks that have high variability in the background. Finally, we introduce a forgetfulness measure that fairly evaluates the degree to which a model suffers from forgetting. Interestingly, the analysis of our proposed forgetfulness score also implies that FoCL tends to have a mitigated forgetting for future tasks. |
| Tasks | Continual Learning |
| Published | 2020-03-09 |
| URL | https://arxiv.org/abs/2003.03877v1 |
| https://arxiv.org/pdf/2003.03877v1.pdf | |
| PWC | https://paperswithcode.com/paper/focl-feature-oriented-continual-learning-for |
| Repo | |
| Framework | |
Revisiting Spatial Invariance with Low-Rank Local Connectivity
| Title | Revisiting Spatial Invariance with Low-Rank Local Connectivity |
| Authors | Gamaleldin F. Elsayed, Prajit Ramachandran, Jonathon Shlens, Simon Kornblith |
| Abstract | Convolutional neural networks are among the most successful architectures in deep learning. This success is at least partially attributable to the efficacy of spatial invariance as an inductive bias. Locally connected layers, which differ from convolutional layers in their lack of spatial invariance, usually perform poorly in practice. However, these observations still leave open the possibility that some degree of relaxation of spatial invariance may yield a better inductive bias than either convolution or local connectivity. To test this hypothesis, we design a method to relax the spatial invariance of a network layer in a controlled manner. In particular, we create a \textit{low-rank} locally connected layer, where the filter bank applied at each position is constructed as a linear combination of basis set of filter banks. By varying the number of filter banks in the basis set, we can control the degree of departure from spatial invariance. In our experiments, we find that relaxing spatial invariance improves classification accuracy over both convolution and locally connected layers across MNIST, CIFAR-10, and CelebA datasets. These results suggest that spatial invariance in convolution layers may be overly restrictive. |
| Tasks | |
| Published | 2020-02-07 |
| URL | https://arxiv.org/abs/2002.02959v1 |
| https://arxiv.org/pdf/2002.02959v1.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-spatial-invariance-with-low-rank |
| Repo | |
| Framework | |
Utilizing Language Relatedness to improve Machine Translation: A Case Study on Languages of the Indian Subcontinent
| Title | Utilizing Language Relatedness to improve Machine Translation: A Case Study on Languages of the Indian Subcontinent |
| Authors | Anoop Kunchukuttan, Pushpak Bhattacharyya |
| Abstract | In this work, we present an extensive study of statistical machine translation involving languages of the Indian subcontinent. These languages are related by genetic and contact relationships. We describe the similarities between Indic languages arising from these relationships. We explore how lexical and orthographic similarity among these languages can be utilized to improve translation quality between Indic languages when limited parallel corpora is available. We also explore how the structural correspondence between Indic languages can be utilized to re-use linguistic resources for English to Indic language translation. Our observations span 90 language pairs from 9 Indic languages and English. To the best of our knowledge, this is the first large-scale study specifically devoted to utilizing language relatedness to improve translation between related languages. |
| Tasks | Machine Translation |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08925v1 |
| https://arxiv.org/pdf/2003.08925v1.pdf | |
| PWC | https://paperswithcode.com/paper/utilizing-language-relatedness-to-improve |
| Repo | |
| Framework | |
Metaplasticity in Multistate Memristor Synaptic Networks
| Title | Metaplasticity in Multistate Memristor Synaptic Networks |
| Authors | Fatima Tuz Zohora, Abdullah M. Zyarah, Nicholas Soures, Dhireesha Kudithipudi |
| Abstract | Recent studies have shown that metaplastic synapses can retain information longer than simple binary synapses and are beneficial for continual learning. In this paper, we explore the multistate metaplastic synapse characteristics in the context of high retention and reception of information. Inherent behavior of a memristor emulating the multistate synapse is employed to capture the metaplastic behavior. An integrated neural network study for learning and memory retention is performed by integrating the synapse in a $5\times3$ crossbar at the circuit level and $128\times128$ network at the architectural level. An on-device training circuitry ensures the dynamic learning in the network. In the $128\times128$ network, it is observed that the number of input patterns the multistate synapse can classify is $\simeq$ 2.1x that of a simple binary synapse model, at a mean accuracy of $\geq$ 75% . |
| Tasks | Continual Learning |
| Published | 2020-02-26 |
| URL | https://arxiv.org/abs/2003.11638v1 |
| https://arxiv.org/pdf/2003.11638v1.pdf | |
| PWC | https://paperswithcode.com/paper/metaplasticity-in-multistate-memristor |
| Repo | |
| Framework | |
Using Hindsight to Anchor Past Knowledge in Continual Learning
| Title | Using Hindsight to Anchor Past Knowledge in Continual Learning |
| Authors | Arslan Chaudhry, Albert Gordo, Puneet K. Dokania, Philip Torr, David Lopez-Paz |
| Abstract | In continual learning, the learner faces a stream of data whose distribution changes over time. Modern neural networks are known to suffer under this setting, as they quickly forget previously acquired knowledge. To address such catastrophic forgetting, many continual learning methods implement different types of experience replay, re-learning on past data stored in a small buffer known as episodic memory. In this work, we complement experience replay with a new objective that we call anchoring, where the learner uses bilevel optimization to update its knowledge on the current task, while keeping intact the predictions on some anchor points of past tasks. These anchor points are learned using gradient-based optimization to maximize forgetting, which is approximated by fine-tuning the currently trained model on the episodic memory of past tasks. Experiments on several supervised learning benchmarks for continual learning demonstrate that our approach improves the standard experience replay in terms of both accuracy and forgetting metrics and for various sizes of episodic memories. |
| Tasks | bilevel optimization, Continual Learning |
| Published | 2020-02-19 |
| URL | https://arxiv.org/abs/2002.08165v1 |
| https://arxiv.org/pdf/2002.08165v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-hindsight-to-anchor-past-knowledge-in-1 |
| Repo | |
| Framework | |
Learning the Designer’s Preferences to Drive Evolution
| Title | Learning the Designer’s Preferences to Drive Evolution |
| Authors | Alberto Alvarez, Jose Font |
| Abstract | This paper presents the Designer Preference Model, a data-driven solution that pursues to learn from user generated data in a Quality-Diversity Mixed-Initiative Co-Creativity (QD MI-CC) tool, with the aims of modelling the user’s design style to better assess the tool’s procedurally generated content with respect to that user’s preferences. Through this approach, we aim for increasing the user’s agency over the generated content in a way that neither stalls the user-tool reciprocal stimuli loop nor fatigues the user with periodical suggestion handpicking. We describe the details of this novel solution, as well as its implementation in the MI-CC tool the Evolutionary Dungeon Designer. We present and discuss our findings out of the initial tests carried out, spotting the open challenges for this combined line of research that integrates MI-CC with Procedural Content Generation through Machine Learning. |
| Tasks | |
| Published | 2020-03-06 |
| URL | https://arxiv.org/abs/2003.03268v1 |
| https://arxiv.org/pdf/2003.03268v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-the-designers-preferences-to-drive |
| Repo | |
| Framework | |
Similarity of Neural Networks with Gradients
| Title | Similarity of Neural Networks with Gradients |
| Authors | Shuai Tang, Wesley J. Maddox, Charlie Dickens, Tom Diethe, Andreas Damianou |
| Abstract | A suitable similarity index for comparing learnt neural networks plays an important role in understanding the behaviour of the highly-nonlinear functions, and can provide insights on further theoretical analysis and empirical studies. We define two key steps when comparing models: firstly, the representation abstracted from the learnt model, where we propose to leverage both feature vectors and gradient ones (which are largely ignored in prior work) into designing the representation of a neural network. Secondly, we define the employed similarity index which gives desired invariance properties, and we facilitate the chosen ones with sketching techniques for comparing various datasets efficiently. Empirically, we show that the proposed approach provides a state-of-the-art method for computing similarity of neural networks that are trained independently on different datasets and the tasks defined by the datasets. |
| Tasks | |
| Published | 2020-03-25 |
| URL | https://arxiv.org/abs/2003.11498v1 |
| https://arxiv.org/pdf/2003.11498v1.pdf | |
| PWC | https://paperswithcode.com/paper/similarity-of-neural-networks-with-gradients |
| Repo | |
| Framework | |
On Hyper-parameter Tuning for Stochastic Optimization Algorithms
| Title | On Hyper-parameter Tuning for Stochastic Optimization Algorithms |
| Authors | Haotian Zhang, Jianyong Sun, Zongben Xu |
| Abstract | This paper proposes the first-ever algorithmic framework for tuning hyper-parameters of stochastic optimization algorithm based on reinforcement learning. Hyper-parameters impose significant influences on the performance of stochastic optimization algorithms, such as evolutionary algorithms (EAs) and meta-heuristics. Yet, it is very time-consuming to determine optimal hyper-parameters due to the stochastic nature of these algorithms. We propose to model the tuning procedure as a Markov decision process, and resort the policy gradient algorithm to tune the hyper-parameters. Experiments on tuning stochastic algorithms with different kinds of hyper-parameters (continuous and discrete) for different optimization problems (continuous and discrete) show that the proposed hyper-parameter tuning algorithms do not require much less running times of the stochastic algorithms than bayesian optimization method. The proposed framework can be used as a standard tool for hyper-parameter tuning in stochastic algorithms. |
| Tasks | Stochastic Optimization |
| Published | 2020-03-04 |
| URL | https://arxiv.org/abs/2003.02038v2 |
| https://arxiv.org/pdf/2003.02038v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-hyper-parameter-tuning-for-stochastic |
| Repo | |
| Framework | |
Generating Automatic Curricula via Self-Supervised Active Domain Randomization
| Title | Generating Automatic Curricula via Self-Supervised Active Domain Randomization |
| Authors | Sharath Chandra Raparthy, Bhairav Mehta, Florian Golemo, Liam Paull |
| Abstract | Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal. Goal-directed RL has seen large gains in sample efficiency, due to the ease of reusing or generating new experience by proposing goals. In this work, we build on the framework of self-play, allowing an agent to interact with itself in order to make progress on some unknown task. We use Active Domain Randomization and self-play to create a novel, coupled environment-goal curriculum, where agents learn through progressively more difficult tasks and environment variations. Our method, Self-Supervised Active Domain Randomization (SS-ADR), generates a growing curriculum, encouraging the agent to try tasks that are just outside of its current capabilities, while building a domain-randomization curriculum that enables state-of-the-art results on various sim2real transfer tasks. Our results show that a curriculum of co-evolving the environment difficulty along with the difficulty of goals set in each environment provides practical benefits in the goal-directed tasks tested. |
| Tasks | |
| Published | 2020-02-18 |
| URL | https://arxiv.org/abs/2002.07911v1 |
| https://arxiv.org/pdf/2002.07911v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-automatic-curricula-via-self |
| Repo | |
| Framework | |
Nonlinear Traffic Prediction as a Matrix Completion Problem with Ensemble Learning
| Title | Nonlinear Traffic Prediction as a Matrix Completion Problem with Ensemble Learning |
| Authors | Wenqing Li, Chuhan Yang, Saif Eddin Jabari |
| Abstract | We focus on short-term traffic forecasting for traffic operations management. Specifically, we focus on forecasting traffic network sensor states in high-resolution (second-by-second). Most work on traffic forecasting has focused on predicting aggregated traffic variables, typically over intervals that are no shorter than 5 minutes. The data resolution required for traffic operations is challenging since high-resolution data exhibit heavier oscillations and precise patterns are harder to capture. We propose a (big) data-driven methodology for this purpose. Our contributions can be summarized as offering three major insights: first, we show how the forecasting problem can be modeled as a matrix completion problem. Second, we employ a block-coordinate descent algorithm and demonstrate that the algorithm converges in sub-linear time to a block coordinate-wise optimizer. This allows us to capitalize on the “bigness” of high-resolution data in a computationally feasible way. Third, we develop an adaptive boosting (or ensemble learning) approach to reduce the training error to within any arbitrary error threshold. The latter utilizes past days so that the boosting can be interpreted as capturing periodic patterns in the data. The performance of the proposed method is analyzed theoretically and tested empirically using a real-world high-resolution traffic dataset from Abu Dhabi, UAE. Our experimental results show that the proposed method outperforms other state-of-the-art algorithms. |
| Tasks | Matrix Completion, Traffic Prediction |
| Published | 2020-01-08 |
| URL | https://arxiv.org/abs/2001.02492v2 |
| https://arxiv.org/pdf/2001.02492v2.pdf | |
| PWC | https://paperswithcode.com/paper/nonlinear-traffic-prediction-as-a-matrix |
| Repo | |
| Framework | |
Large-Scale Shrinkage Estimation under Markovian Dependence
| Title | Large-Scale Shrinkage Estimation under Markovian Dependence |
| Authors | Bowen Gang, Gourab Mukherjee, Wenguang Sun |
| Abstract | We consider the problem of simultaneous estimation of a sequence of dependent parameters that are generated from a hidden Markov model. Based on observing a noise contaminated vector of observations from such a sequence model, we consider simultaneous estimation of all the parameters irrespective of their hidden states under square error loss. We study the roles of statistical shrinkage for improved estimation of these dependent parameters. Being completely agnostic on the distributional properties of the unknown underlying Hidden Markov model, we develop a novel non-parametric shrinkage algorithm. Our proposed method elegantly combines \textit{Tweedie}-based non-parametric shrinkage ideas with efficient estimation of the hidden states under Markovian dependence. Based on extensive numerical experiments, we establish superior performance our our proposed algorithm compared to non-shrinkage based state-of-the-art parametric as well as non-parametric algorithms used in hidden Markov models. We provide decision theoretic properties of our methodology and exhibit its enhanced efficacy over popular shrinkage methods built under independence. We demonstrate the application of our methodology on real-world datasets for analyzing of temporally dependent social and economic indicators such as search trends and unemployment rates as well as estimating spatially dependent Copy Number Variations. |
| Tasks | |
| Published | 2020-03-04 |
| URL | https://arxiv.org/abs/2003.01873v2 |
| https://arxiv.org/pdf/2003.01873v2.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-shrinkage-estimation-under |
| Repo | |
| Framework | |
Reducing the Computational Burden of Deep Learning with Recursive Local Representation Alignment
| Title | Reducing the Computational Burden of Deep Learning with Recursive Local Representation Alignment |
| Authors | Alexander Ororbia, Ankur Mali, Daniel Kifer, C. Lee Giles |
| Abstract | Training deep neural networks on large-scale datasets requires significant hardware resources whose costs (even on cloud platforms) put them out of reach of smaller organizations, groups, and individuals. Backpropagation (backprop), the workhorse for training these networks, is an inherently sequential process that is difficult to parallelize. Furthermore, it requires researchers to continually develop various tricks, such as specialized weight initializations and activation functions, in order to ensure a stable parameter optimization. Our goal is to seek an effective, parallelizable alternative to backprop that can be used to train deep networks. In this paper, we propose a gradient-free learning procedure, recursive local representation alignment, for training large-scale neural architectures. Experiments with deep residual networks on CIFAR-10 and the massive-scale benchmark, ImageNet, show that our algorithm generalizes as well as backprop while converging sooner due to weight updates that are parallelizable and computationally less demanding. This is empirical evidence that a backprop-free algorithm can scale up to larger datasets. Another contribution is that we also significantly reduce total parameter count of our networks by utilizing fast, fixed noise maps in place of convolutional operations without compromising generalization. |
| Tasks | |
| Published | 2020-02-10 |
| URL | https://arxiv.org/abs/2002.03911v1 |
| https://arxiv.org/pdf/2002.03911v1.pdf | |
| PWC | https://paperswithcode.com/paper/reducing-the-computational-burden-of-deep |
| Repo | |
| Framework | |
Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
| Title | Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only |
| Authors | Qi Chen, Qi Wu, Rui Tang, Yuhan Wang, Shuai Wang, Mingkui Tan |
| Abstract | Home design is a complex task that normally requires architects to finish with their professional skills and tools. It will be fascinating that if one can produce a house plan intuitively without knowing much knowledge about home design and experience of using complex designing tools, for example, via natural language. In this paper, we formulate it as a language conditioned visual content generation problem that is further divided into a floor plan generation and an interior texture (such as floor and wall) synthesis task. The only control signal of the generation process is the linguistic expression given by users that describe the house details. To this end, we propose a House Plan Generative Model (HPGM) that first translates the language input to a structural graph representation and then predicts the layout of rooms with a Graph Conditioned Layout Prediction Network (GC LPN) and generates the interior texture with a Language Conditioned Texture GAN (LCT-GAN). With some post-processing, the final product of this task is a 3D house model. To train and evaluate our model, we build the first Text-to-3D House Model dataset. |
| Tasks | |
| Published | 2020-03-01 |
| URL | https://arxiv.org/abs/2003.00397v1 |
| https://arxiv.org/pdf/2003.00397v1.pdf | |
| PWC | https://paperswithcode.com/paper/intelligent-home-3d-automatic-3d-house-design |
| Repo | |
| Framework | |
A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection
| Title | A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection |
| Authors | Daniele Bonadiman, Alessandro Moschitti |
| Abstract | An essential task of most Question Answering (QA) systems is to re-rank the set of answer candidates, i.e., Answer Sentence Selection (A2S). These candidates are typically sentences either extracted from one or more documents preserving their natural order or retrieved by a search engine. Most state-of-the-art approaches to the task use huge neural models, such as BERT, or complex attentive architectures. In this paper, we argue that by exploiting the intrinsic structure of the original rank together with an effective word-relatedness encoder, we can achieve competitive results with respect to the state of the art while retaining high efficiency. Our model takes 9.5 seconds to train on the WikiQA dataset, i.e., very fast in comparison with the $\sim 18$ minutes required by a standard BERT-base fine-tuning. |
| Tasks | Question Answering |
| Published | 2020-03-04 |
| URL | https://arxiv.org/abs/2003.02349v1 |
| https://arxiv.org/pdf/2003.02349v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-study-on-efficiency-accuracy-and-document |
| Repo | |
| Framework | |
