Parameter estimation/optimization

Low-variance estimation in the Plackett-Luce model via quasi-Monte Carlo sampling

Alexander Buchholz, Jan Malte Lichtenberg, Giuseppe Di Benedetto, Yannik Stein, Vito Bellini, Matteo Ruffini

SIGIR 2022 Workshop on Reaching Efficiency in Neural Information Retrieval

2022

The Plackett-Luce (PL) model is popular in learning-to-rank (LTR) because it provides a useful and intuitive probabilistic model for sampling ranked lists. Counterfactual offline evaluation and optimization of ranking metrics are pivotal for using LTR methods in production. When adopting the PL model as a ranking policy, both tasks require the computation of expectations with respect to the model. These

Machine learning

Clock skew robust acoustic echo cancellation

Karim Helwani, Erfan Soltanmohammadi, Michael M. Goodwin, Arvindh Krishnaswamy

Interspeech 2022

2022

Traditional acoustic echo cancelers require that the reference and microphone signals have exactly the same sampling frequency. In this paper, we present a novel Kalman filtering approach to acoustic echo cancellation (AEC) which blindly accounts for the clock skew between the playback and recording devices without the need for exchanging timestamps when they have independent clocks. The proposed Kalman-filter

Machine learning

Targeted separation and convergence with kernel discrepancies

Alessandro Barp, Carl-Johann Simon-Gabriel, Mark Girolami, Lester Mackey

NeurIPS 2022 Workshop on Score-Based Methods

2022

Kernel Stein discrepancies (KSDs) are maximum mean discrepancies (MMDs) that leverage the score information of distributions, and have grown central to a wide range of applications. In most settings, these MMDs are required to (i) separate a target P from other probability measures or even (ii) control weak convergence to P. In this article we derive new sufficient and necessary conditions that substantially

Machine learning

Towards multi-objective statistically fair federated learning

Ninareh Mehrabi, Cyprien de Lichy, John McKay, Cynthia He, William M. Campbell

AAAI 2022 Workshop on Trustable, Verifiable and Auditable Federated Learning (FL-AAAI-22)

2022

Federated Learning (FL) has emerged as a result of data ownership and privacy concerns to prevent data from being shared between multiple parties included in a training procedure. Although issues, such as privacy, have gained significant attention in this domain, not much attention has been given to satisfying statistical fairness measures in the FL setting. With this goal in mind, we conduct studies to

Machine learning

Training mixed-domain translation models via federated learning

Peyman Passban, Tanya Roosta, Rahul Gupta, Ankit Chadha, Clement Chung

NAACL 2022

2022

Training mixed-domain translation models is a complex task that demands tailored architectures and costly data preparation techniques. In this work, we leverage federated learning (FL) in order to tackle the problem. Our investigation demonstrates that with slight modifications in the training process, neural machine translation (NMT) engines can be easily adapted when an FL-based aggregation is applied

Machine learning

Partial model averaging in federated learning: Performance guarantees and benefits

Sunwoo Lee, Anit Kumar Sahu, Chaoyang He, Salman Avestimehr

AAAI 2022 Workshop on Trustable, Verifiable and Auditable Federated Learning (FL-AAAI-22)

2022

Local Stochastic Gradient Descent (SGD) with periodic model averaging (FedAvg) is a foundational algorithm in Federated Learning. The algorithm independently runs SGD on multiple workers and periodically averages the model across all the workers. When local SGD runs with many workers, however, the periodic averaging causes a significant model discrepancy across the workers making the global loss converge

Machine learning

Bridging recommendation and marketing via recurrent intensity modeling

Yifei Ma, Ge Liu, Anoop Deoras

ICLR 2022

2022

This paper studies some unexplored connections between personalized recommendation and marketing systems. Obviously, the two systems are different, in two main ways. Firstly, personalized item-recommendation (ItemRec) is user-centric, whereas marketing recommends the best user-state segments (UserRec) on behalf of its item providers. (We treat different temporal states of the same user as separate marketing

Machine learning

Spherical harmonic covariance and magnitude function encodings for beamformer design

Mike Luo

EURASIP Journal on Audio, Speech, and Music Processing

2022

Microphone and speaker array designs have increasingly diverged from simple topologies due to diversity of physical host geometries and use cases. Effective beamformer design must now account for variation in the array’s acoustic radiation pattern, spatial distribution of target and noise sources, and intended beampattern directivity. Relevant tasks such as representing complex pressure fields, specifying

Robotics

Sparse recovery of acoustic waves

Mohamed Mansour

ICASSP 2022

2022

We present a general model for acoustic wave decomposition (AWD) on a rigid surface for a general microphone array configuration. The decomposition is modeled as a sparse recovery optimization problem that is independent of the shape of the rigid surface or the microphone array geometry. We describe an efficient algorithm for solving the optimization problem for broadband signals, and establish its effectiveness

Conversational AI

Symbolic music generation with transformer-GANs

Aashiq Muhamed, Liang Li, Xingjian Shi, Suri Yaddanapudi, Wayne Chi, Dylan Jackson, Rahul Suresh, Zachary Lipton, Alex Smola

2021

Transformers have emerged as the dominant approach in music literature for generating minute-long compositions with compelling musical structure. These models are trained by minimizing the negative log-likelihood (NLL) of the observed sequence autoregressively. Unfortunately, the quality of samples from these models tends to degrade significantly for long sequences, a phenomenon attributed to exposure bias

Conversational AI

Parameter estimation/optimization

Work with us