Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Recommendation": models, code, and papers

Competing AI: How competition feedback affects machine learning

Oct 02, 2020
Antonio Ginart, Eva Zhang, Yongchan Kwon, James Zou

This papers studies how competition affects machine learning (ML) predictors. As ML becomes more ubiquitous, it is often deployed by companies to compete over customers. For example, digital platforms like Yelp use ML to predict user preference and make recommendations. A service that is more often queried by users, perhaps because it more accurately anticipates user preferences, is also more likely to obtain additional user data (e.g. in the form of a Yelp review). Thus, competing predictors cause feedback loops whereby a predictor's performance impacts what training data it receives and biases its predictions over time. We introduce a flexible model of competing ML predictors that enables both rapid experimentation and theoretical tractability. We show with empirical and mathematical analysis that competition causes predictors to specialize for specific sub-populations at the cost of worse performance over the general population. We further analyze the impact of predictor specialization on the overall prediction quality experienced by users. We show that having too few or too many competing predictors in a market can hurt the overall prediction quality. Our theory is complemented by experiments on several real datasets using popular learning algorithms, such as neural networks and nearest neighbor methods.

* Manuscript 

  Access Paper or Ask Questions

Thompson Sampling for Combinatorial Semi-bandits with Sleeping Arms and Long-Term Fairness Constraints

May 14, 2020
Zhiming Huang, Yifan Xu, Bingshan Hu, Qipeng Wang, Jianping Pan

We study the combinatorial sleeping multi-armed semi-bandit problem with long-term fairness constraints~(CSMAB-F). To address the problem, we adopt Thompson Sampling~(TS) to maximize the total rewards and use virtual queue techniques to handle the fairness constraints, and design an algorithm called \emph{TS with beta priors and Bernoulli likelihoods for CSMAB-F~(TSCSF-B)}. Further, we prove TSCSF-B can satisfy the fairness constraints, and the time-averaged regret is upper bounded by $\frac{N}{2\eta} + O\left(\frac{\sqrt{mNT\ln T}}{T}\right)$, where $N$ is the total number of arms, $m$ is the maximum number of arms that can be pulled simultaneously in each round~(the cardinality constraint) and $\eta$ is the parameter trading off fairness for rewards. By relaxing the fairness constraints (i.e., let $\eta \rightarrow \infty$), the bound boils down to the first problem-independent bound of TS algorithms for combinatorial sleeping multi-armed semi-bandit problems. Finally, we perform numerical experiments and use a high-rating movie recommendation application to show the effectiveness and efficiency of the proposed algorithm.

  Access Paper or Ask Questions

Adversarial examples and where to find them

Apr 22, 2020
Niklas Risse, Christina Göpfert, Jan Philip Göpfert

Adversarial robustness of trained models has attracted considerable attention over recent years, within and beyond the scientific community. This is not only because of a straight-forward desire to deploy reliable systems, but also because of how adversarial attacks challenge our beliefs about deep neural networks. Demanding more robust models seems to be the obvious solution -- however, this requires a rigorous understanding of how one should judge adversarial robustness as a property of a given model. In this work, we analyze where adversarial examples occur, in which ways they are peculiar, and how they are processed by robust models. We use robustness curves to show that $\ell_\infty$ threat models are surprisingly effective in improving robustness for other $\ell_p$ norms; we introduce perturbation cost trajectories to provide a broad perspective on how robust and non-robust networks perceive adversarial perturbations as opposed to random perturbations; and we explicitly examine the scale of certain common data sets, showing that robustness thresholds must be adapted to the data set they pertain to. This allows us to provide concrete recommendations for anyone looking to train a robust model or to estimate how much robustness they should require for their operation. The code for all our experiments is available at .

  Access Paper or Ask Questions

The value of text for small business default prediction: A deep learning approach

Mar 19, 2020
Matthew Stevenson, Christophe Mues, Cristián Bravo

Compared to consumer lending, Micro, Small and Medium Enterprise (mSME) credit risk modelling is particularly challenging, as, often, the same sources of information are not available. To mitigate limited data availability, it is standard policy for a loan officer to provide a textual loan assessment. In turn, this statement is analysed by a credit expert alongside any available standard credit data. In our paper, we exploit recent advances from the field of Deep Learning and Natural Language Processing (NLP), including the BERT (Bidirectional Encoder Representations from Transformers) model, to extract information from 60000+ textual assessments. We consider the performance in terms of AUC (Area Under the Curve) and Balanced Accuracy and find that the text alone is surprisingly effective for predicting default. Yet, when combined with traditional data, it yields no additional predictive capability. We do find, however, that deep learning with categorical embeddings is capable of producing a modest performance improvement when compared to alternative machine learning models. We explore how the loan assessments influence predictions, explaining why despite the text being predictive, no additional performance is gained. This exploration leads us to a series of recommendations on a new strategy for the collection of future mSME loan assessments.

* Submitted - v1 

  Access Paper or Ask Questions

Enhancing VAEs for Collaborative Filtering: Flexible Priors & Gating Mechanisms

Nov 03, 2019
Daeryong Kim, Bongwon Suh

Neural network based models for collaborative filtering have started to gain attention recently. One branch of research is based on using deep generative models to model user preferences where variational autoencoders were shown to produce state-of-the-art results. However, there are some potentially problematic characteristics of the current variational autoencoder for CF. The first is the too simplistic prior that VAEs incorporate for learning the latent representations of user preference. The other is the model's inability to learn deeper representations with more than one hidden layer for each network. Our goal is to incorporate appropriate techniques to mitigate the aforementioned problems of variational autoencoder CF and further improve the recommendation performance. Our work is the first to apply flexible priors to collaborative filtering and show that simple priors (in original VAEs) may be too restrictive to fully model user preferences and setting a more flexible prior gives significant gains. We experiment with the VampPrior, originally proposed for image generation, to examine the effect of flexible priors in CF. We also show that VampPriors coupled with gating mechanisms outperform SOTA results including the Variational Autoencoder for Collaborative Filtering by meaningful margins on 2 popular benchmark datasets (MovieLens & Netflix).

* In Thirteenth ACM Conference on Recommender Systems (RecSys '19), September 16-20, 2019, Copenhagen, Denmark. ACM, New York, NY, USA, 5 pages 

  Access Paper or Ask Questions

A Study of BFLOAT16 for Deep Learning Training

Jun 13, 2019
Dhiraj Kalamkar, Dheevatsa Mudigere, Naveen Mellempudi, Dipankar Das, Kunal Banerjee, Sasikanth Avancha, Dharma Teja Vooturi, Nataraj Jammalamadaka, Jianyu Huang, Hector Yuen, Jiyan Yang, Jongsoo Park, Alexander Heinecke, Evangelos Georganas, Sudarshan Srinivasan, Abhisek Kundu, Misha Smelyanskiy, Bharat Kaul, Pradeep Dubey

This paper presents the first comprehensive empirical study demonstrating the efficacy of the Brain Floating Point (BFLOAT16) half-precision format for Deep Learning training across image classification, speech recognition, language modeling, generative networks and industrial recommendation systems. BFLOAT16 is attractive for Deep Learning training for two reasons: the range of values it can represent is the same as that of IEEE 754 floating-point format (FP32) and conversion to/from FP32 is simple. Maintaining the same range as FP32 is important to ensure that no hyper-parameter tuning is required for convergence; e.g., IEEE 754 compliant half-precision floating point (FP16) requires hyper-parameter tuning. In this paper, we discuss the flow of tensors and various key operations in mixed precision training, and delve into details of operations, such as the rounding modes for converting FP32 tensors to BFLOAT16. We have implemented a method to emulate BFLOAT16 operations in Tensorflow, Caffe2, IntelCaffe, and Neon for our experiments. Our results show that deep learning training using BFLOAT16 tensors achieves the same state-of-the-art (SOTA) results across domains as FP32 tensors in the same number of iterations and with no changes to hyper-parameters.

  Access Paper or Ask Questions

Stochastic Bandit Models for Delayed Conversions

Jul 12, 2017
Claire Vernade, Olivier Cappé, Vianney Perchet

Online advertising and product recommendation are important domains of applications for multi-armed bandit methods. In these fields, the reward that is immediately available is most often only a proxy for the actual outcome of interest, which we refer to as a conversion. For instance, in web advertising, clicks can be observed within a few seconds after an ad display but the corresponding sale --if any-- will take hours, if not days to happen. This paper proposes and investigates a new stochas-tic multi-armed bandit model in the framework proposed by Chapelle (2014) --based on empirical studies in the field of web advertising-- in which each action may trigger a future reward that will then happen with a stochas-tic delay. We assume that the probability of conversion associated with each action is unknown while the distribution of the conversion delay is known, distinguishing between the (idealized) case where the conversion events may be observed whatever their delay and the more realistic setting in which late conversions are censored. We provide performance lower bounds as well as two simple but efficient algorithms based on the UCB and KLUCB frameworks. The latter algorithm, which is preferable when conversion rates are low, is based on a Poissonization argument, of independent interest in other settings where aggregation of Bernoulli observations with different success probabilities is required.

* Conference on Uncertainty in Artificial Intelligence, Aug 2017, Sydney, Australia 

  Access Paper or Ask Questions

Adversarial Machine Learning at Scale

Feb 11, 2017
Alexey Kurakin, Ian Goodfellow, Samy Bengio

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial training is the process of explicitly training a model on adversarial examples, in order to make it more robust to attack or to reduce its test error on clean inputs. So far, adversarial training has primarily been applied to small problems. In this research, we apply adversarial training to ImageNet. Our contributions include: (1) recommendations for how to succesfully scale adversarial training to large models and datasets, (2) the observation that adversarial training confers robustness to single-step attack methods, (3) the finding that multi-step attack methods are somewhat less transferable than single-step attack methods, so single-step attacks are the best for mounting black-box attacks, and (4) resolution of a "label leaking" effect that causes adversarially trained models to perform better on adversarial examples than on clean examples, because the adversarial example construction process uses the true label and the model can learn to exploit regularities in the construction process.

* 17 pages, 5 figures 

  Access Paper or Ask Questions

Consistency and fluctuations for stochastic gradient Langevin dynamics

Jun 12, 2015
Yee Whye Teh, Alexandre Thiéry, Sebastian Vollmer

Applying standard Markov chain Monte Carlo (MCMC) algorithms to large data sets is computationally expensive. Both the calculation of the acceptance probability and the creation of informed proposals usually require an iteration through the whole data set. The recently proposed stochastic gradient Langevin dynamics (SGLD) method circumvents this problem by generating proposals which are only based on a subset of the data, by skipping the accept-reject step and by using decreasing step-sizes sequence $(\delta_m)_{m \geq 0}$. %Under appropriate Lyapunov conditions, We provide in this article a rigorous mathematical framework for analysing this algorithm. We prove that, under verifiable assumptions, the algorithm is consistent, satisfies a central limit theorem (CLT) and its asymptotic bias-variance decomposition can be characterized by an explicit functional of the step-sizes sequence $(\delta_m)_{m \geq 0}$. We leverage this analysis to give practical recommendations for the notoriously difficult tuning of this algorithm: it is asymptotically optimal to use a step-size sequence of the type $\delta_m \asymp m^{-1/3}$, leading to an algorithm whose mean squared error (MSE) decreases at rate $\mathcal{O}(m^{-1/3})$

* 35 pages, 5 figures 

  Access Paper or Ask Questions