In this paper we present the results of our experiments in training and deploying a self-supervised retrieval-based chatbot trained with contrastive learning for assisting customer support agents. In contrast to most existing research papers in this area where the focus is on solving just one component of a deployable chatbot, we present an end-to-end set of solutions to take the reader from an unlabelled chatlogs to a deployed chatbot. This set of solutions includes creating a self-supervised dataset and a weakly labelled dataset from chatlogs, as well as a systematic approach to selecting a fixed list of canned responses. We present a hierarchical-based RNN architecture for the response selection model, chosen for its ability to cache intermediate utterance embeddings, which helped to meet deployment inference speed requirements. We compare the performance of this architecture across 3 different learning objectives: self-supervised contrastive learning, binary classification, and multi-class classification. We find that using a self-supervised contrastive learning model outperforms training the binary and multi-class classification models on a weakly labelled dataset. Our results validate that the self-supervised contrastive learning approach can be effectively used for a real-world chatbot scenario.

Many machine learning tasks involve subpopulation shift where the testing data distribution is a subpopulation of the training distribution. For such settings, a line of recent work has proposed the use of a variant of empirical risk minimization(ERM) known as distributionally robust optimization (DRO). In this work, we apply DRO to real, large-scale tasks with subpopulation shift, and observe that DRO performs relatively poorly, and moreover has severe instability. We identify one direct cause of this phenomenon: sensitivity of DRO to outliers in the datasets. To resolve this issue, we propose the framework of DORO, for Distributional and Outlier Robust Optimization. At the core of this approach is a refined risk function which prevents DRO from overfitting to potential outliers. We instantiate DORO for the Cressie-Read family of R\'enyi divergence, and delve into two specific instances of this family: CVaR and $\chi^2$-DRO. We theoretically prove the effectiveness of the proposed method, and empirically show that DORO improves the performance and stability of DRO with experiments on large modern datasets, thereby positively addressing the open question raised by Hashimoto et al., 2018.

We introduce a new scalable variational Gaussian process approximation which provides a high fidelity approximation while retaining general applicability. We propose the harmonic kernel decomposition (HKD), which uses Fourier series to decompose a kernel as a sum of orthogonal kernels. Our variational approximation exploits this orthogonality to enable a large number of inducing points at a low computational cost. We demonstrate that, on a range of regression and classification problems, our approach can exploit input space symmetries such as translations and reflections, and it significantly outperforms standard variational methods in scalability and accuracy. Notably, our approach achieves state-of-the-art results on CIFAR-10 among pure GP models.

In this paper, we propose a realistic multiple dynamic pricing approach to demand response in the retail market. First, an adaptive clustering-based customer segmentation framework is proposed to categorize customers into different groups to enable the effective identification of usage patterns. Second, customized demand models with important market constraints which capture the price-demand relationship explicitly, are developed for each group of customers to improve the model accuracy and enable meaningful pricing. Third, the multiple pricing based demand response is formulated as a profit maximization problem subject to realistic market constraints. The overall aim of the proposed scalable and practical method aims to achieve 'right' prices for 'right' customers so as to benefit various stakeholders in the system such as grid operators, customers and retailers. The proposed multiple pricing framework is evaluated via simulations based on real-world datasets.

Deep learning (DL) based language models achieve high performance on various benchmarks for Natural Language Inference (NLI). And at this time, symbolic approaches to NLI are receiving less attention. Both approaches (symbolic and DL) have their advantages and weaknesses. However, currently, no method combines them in a system to solve the task of NLI. To merge symbolic and deep learning methods, we propose an inference framework called NeuralLog, which utilizes both a monotonicity-based logical inference engine and a neural network language model for phrase alignment. Our framework models the NLI task as a classic search problem and uses the beam search algorithm to search for optimal inference paths. Experiments show that our joint logic and neural inference system improves accuracy on the NLI task and can achieve state-of-art accuracy on the SICK and MED datasets.

Variational Bayes (VB) is a critical method in machine learning and statistics, underpinning the recent success of Bayesian deep learning. The natural gradient is an essential component of efficient VB estimation, but it is prohibitively computationally expensive in high dimensions. We propose a hybrid quantum-classical algorithm to improve the scaling properties of natural gradient computation and make VB a truly computationally efficient method for Bayesian inference in highdimensional settings. The algorithm leverages matrix inversion from the linear systems algorithm by Harrow, Hassidim, and Lloyd [Phys. Rev. Lett. 103, 15 (2009)] (HHL). We demonstrate that the matrix to be inverted is sparse and the classical-quantum-classical handoffs are sufficiently economical to preserve computational efficiency, making the problem of natural gradient for VB an ideal application of HHL. We prove that, under standard conditions, the VB algorithm with quantum natural gradient is guaranteed to converge.

Algorithms implementing populations of agents which interact with one another and sense their environment may exhibit emergent behavior such as self-organization and swarm intelligence. Here a swarm system, called Databionic swarm (DBS), is introduced which is able to adapt itself to structures of high-dimensional data characterized by distance and/or density-based structures in the data space. By exploiting the interrelations of swarm intelligence, self-organization and emergence, DBS serves as an alternative approach to the optimization of a global objective function in the task of clustering. The swarm omits the usage of a global objective function and is parameter-free because it searches for the Nash equilibrium during its annealing process. To our knowledge, DBS is the first swarm combining these approaches. Its clustering can outperform common clustering methods such as K-means, PAM, single linkage, spectral clustering, model-based clustering, and Ward, if no prior knowledge about the data is available. A central problem in clustering is the correct estimation of the number of clusters. This is addressed by a DBS visualization called topographic map which allows assessing the number of clusters. It is known that all clustering algorithms construct clusters, irrespective of the data set contains clusters or not. In contrast to most other clustering algorithms, the topographic map identifies, that clustering of the data is meaningless if the data contains no (natural) clusters. The performance of DBS is demonstrated on a set of benchmark data, which are constructed to pose difficult clustering problems and in two real-world applications.

Deployed in over 80 per cent of the gaming venues in South Australia, the new solution is part of the state's gambling law reforms to protect the community from the potential harmful effects of gambling. "We had several critical capabilities that our wireless network solution must meet to support our facial recognition devices," said Fraser Larcombe, Vix Vizion. "It must be robust, bullet-proof secure, with the ability to access each machine from anywhere. We got it all from Cradlepoint and LTE." The South Australian state government established a law reform to consolidate banned individuals lists into a single government-managed list.

Inside a 13th-floor boardroom in downtown San Francisco, the atmosphere was tense. It was November 2015, and Databricks, a two-year-old software company started by a group of seven Berkeley researchers, was long on buzz but short on revenue. The directors awkwardly broached subjects that had been rehashed time and again. The startup had been trying to raise funds for five months, but venture capitalists were keeping it at arm's length, wary of its paltry sales. Seeing no other option, NEA partner Pete Sonsini, an existing investor, raised his hand to save the company with an emergency $30 million injection. Founding CEO Ion Stoica had agreed to step aside and return to his professorship at the University of California, Berkeley. The obvious move was to bring in a seasoned Silicon Valley executive, which is exactly what Databricks' chief competitor Snowflake did twice on its way to a software-record $33 billion IPO in September 2020.

I have ADHD and am what many would consider "underemployed" so obviously spend most of my time on the internet arguing with people on Twitter and watching TikToks. I live and breathe the internet and unfortunately/sadly haven't been able to stop posting since I first created an account on LiveJournal in the year 2002. Me and the internet have had some crazy times together. Like when my OkCupid page ended up on 200 websites of "insane internet dating profiles", or when my website kept getting hacked and diverted to Russian porn for a year. A few years ago I made an online show called Overshare with my friend Jared Jekyll (edited by my fiance – thanks babe!) purely for discussing random weird stuff we find on the internet.