Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.

Neural Machine Translation by Jointly Learning to Align and Translate

Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT-14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous state of the art. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

/pdf/sequence-to-sequence-learning-with-neural-networks-4slgp125no.pdf

Sequence to Sequence Learning with Neural Networks

We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Moreover, since the release of the pix2pix software associated with this paper, hundreds of twitter users have posted their own artistic experiments using our system. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without handengineering our loss functions either.

/pdf/image-to-image-translation-with-conditional-adversarial-5058t24et2.pdf

Image-to-Image Translation with Conditional Adversarial Networks

Deep Neural Networks (DNNs) are powerful models that have achieved excellent performance on difficult learning tasks. Although DNNs work well whenever large labeled training sets are available, they cannot be used to map sequences to sequences. In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure. Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector. Our main result is that on an English to French translation task from the WMT'14 dataset, the translations produced by the LSTM achieve a BLEU score of 34.8 on the entire test set, where the LSTM's BLEU score was penalized on out-of-vocabulary words. Additionally, the LSTM did not have difficulty on long sentences. For comparison, a phrase-based SMT system achieves a BLEU score of 33.3 on the same dataset. When we used the LSTM to rerank the 1000 hypotheses produced by the aforementioned SMT system, its BLEU score increases to 36.5, which is close to the previous best result on this task. The LSTM also learned sensible phrase and sentence representations that are sensitive to word order and are relatively invariant to the active and the passive voice. Finally, we found that reversing the order of the words in all source sentences (but not target sentences) improved the LSTM's performance markedly, because doing so introduced many short term dependencies between the source and the target sentence which made the optimization problem easier.

Cluster-based randomized experiments are popular designs for mitigating the bias of standard estimators when interference is present and classical causal inference and experimental design assumptions (such as SUTVA or ITR) do not hold. Without an exact knowledge of the interference structure, it can be challenging to understand which partitioning of the experimental units is optimal to minimize the estimation bias. In the paper, we introduce a monotonicity condition under which a novel two-stage experimental design allows us to determine which of two cluster-based designs yields the least biased estimator. We then consider the setting of online advertising auctions and show that reserve price experiments satisfy the monotonicity condition and the proposed framework and methodology apply. We validate our findings on an advertising auction dataset.

https://dl.acm.org/doi/pdf/10.1145/3219819.3220067

Optimizing Cluster-based Randomized Experiments under Monotonicity

In the Network Inference problem, one seeks to recover the edges of an unknown graph from the observations of cascades propagating over this graph. In this paper, we approach this problem from the sparse recovery perspective. We introduce a general model of cascades, including the voter model and the independent cascade model, for which we provide the first algorithm which recovers the graph's edges with high probability and O(s log m) measurements where s is the maximum degree of the graph and m is the number of nodes. Furthermore, we show that our algorithm also recovers the edge weights (the parameters of the diffusion process) and is robust in the context of approximate sparsity. Finally we prove an almost matching lower bound of Ω(s log m/s) and validate our approach empirically on synthetic graphs.

/pdf/inferring-graphs-from-cascades-a-sparse-recovery-framework-1eq9rllr7c.pdf

Inferring Graphs from Cascades: A Sparse Recovery Framework

Web-based services often run randomized experiments to improve their products. A popular way to run these experiments is to use geographical regions as units of experimentation, since this does not require tracking of individual users or browser cookies. Since users may issue queries from multiple geographical locations, geo-regions cannot be considered independent and interference may be present in the experiment. In this paper, we study this problem, and first present GeoCUTS, a novel algorithm that forms geographical clusters to minimize interference while preserving balance in cluster size. We use a random sample of anonymized traffic from Google Search to form a graph representing user movements, then construct a geographically coherent clustering of the graph. Our main technical contribution is a statistical framework to measure the effectiveness of clusterings. Furthermore, we perform empirical evaluations showing that the performance of GeoCUTS is comparable to hand-crafted geo-regions with respect to both novel and existing metrics.

https://dl.acm.org/doi/pdf/10.1145/3292500.3330778

Randomized Experimental Design via Geographic Clustering

Experimentation platforms are essential to modern large technology companies, as they are used to carry out many randomized experiments daily. The classic assumption of no interference among users, under which the outcome of one user does not depend on the treatment assigned to other users, is rarely tenable on such platforms. Here, we introduce an experimental design strategy for testing whether this assumption holds. Our approach is in the spirit of the Durbin-Wu-Hausman test for endogeneity in econometrics, where multiple estimators return the same estimate if and only if the null hypothesis holds. The design that we introduce makes no assumptions on the interference model between units, nor on the network among the units, and has a sharp bound on the variance and an implied analytical bound on the type I error rate. We discuss how to apply the proposed design strategy to large experimentation platforms, and we illustrate it in the context of an experiment on the LinkedIn platform.

Testing for arbitrary interference on experimentation platforms

Bipartite experiments are a recent object of study in causal inference, whereby treatment is applied to one set of units and outcomes of interest are measured on a different set of units. These experiments are particularly useful in settings where strong interference effects occur between units of a bipartite graph. In market experiments for example, assigning treatment at the seller-level and measuring outcomes at the buyer-level (or vice-versa) may lead to causal models that better account for the interference that naturally occurs between buyers and sellers. While bipartite experiments have been shown to improve the estimation of causal effects in certain settings, the analysis must be done carefully so as to not introduce unnecessary bias. We leverage the generalized propensity score literature to show that we can obtain unbiased estimates of causal effects for bipartite experiments under a standard set of assumptions. We also discuss the construction of confidence sets with proper coverage probabilities. We evaluate these methods using a bipartite graph from a publicly available dataset studied in previous work on bipartite experiments, showing through simulations a significant bias reduction and improved coverage.

Jean Pouget-Abadie

Papers

Optimizing Cluster-based Randomized Experiments under Monotonicity

Inferring Graphs from Cascades: A Sparse Recovery Framework

Randomized Experimental Design via Geographic Clustering

Testing for arbitrary interference on experimentation platforms

Causal Inference with Bipartite Designs.