A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper introduces WHAM! dataset for realistic speech separation in noisy environments.
We propose an algorithm to separate simultaneously speaking persons from each other, the "cocktail party problem", using a single microphone. Our approach involves a deep recurrent neural networks regression to a vector space that is descriptive of independent speakers. Such a vector space can embed empirically determi…
Curvature formulas on regular graphs identified bone idle edges and graphs.
New bounds for average graph distance using curvature and centrality.
Inspired by brain's modality fusion, this paper detects active speakers from audio and video.
We introduce the notion of Bonnet-Myers and Lichnerowicz sharpness in the Ollivier Ricci curvature sense. Our main result is a classification of all self-centered Bonnet-Myers sharp graphs (hypercubes, cocktail party graphs, even-dimensional demi-cubes, Johnson graphs , the Gosset graph and suitable Cartesian …
This paper will describe a novel approach to the cocktail party problem that relies on a fully convolutional neural network (FCN) architecture. The FCN takes noisy audio data as input and performs nonlinear, filtering operations to produce clean audio data of the target speech at the output. Our method learns a model f…
The study bounds the effective diameter of graphs with positive Ollivier curvature.
New method separates music vocals from accompaniment without labeled data.
In this paper, we analyzed how audio-visual speech enhancement can help to perform the ASR task in a cocktail party scenario. Therefore we considered two simple end-to-end LSTM-based models that perform single-channel audio-visual speech enhancement and phone recognition respectively. Then, we studied how the two model…
Deep clustering is a recently introduced deep learning architecture that uses discriminatively trained embeddings as the basis for clustering. It was recently applied to spectrogram segmentation, resulting in impressive results on speaker-independent multi-speaker separation. In this paper we extend the baseline system…
This paper proposes an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within a deep network. Previous approaches, rather than computing a loss on the recons…
A prototypical blind signal separation problem is the so-called cocktail party problem, with n people talking simultaneously and n different microphones within a room. The goal is to recover each speech signal from the microphone inputs. Mathematically this can be modeled by assuming that we are given samples from an n…
Protocol minimizes disclosure in classification tasks.
Privacy-preserving multi-party contextual bandits learn without sharing data.
Differentially-private FNAS protects privacy while collaboratively searching for neural architectures.
We introduce a two-agent problem which is inspired by price asymmetry arising from funding difference. When two parties have different funding rates, the two parties deduce different fair prices for derivative contracts even under the same pricing methodology and parameters. Thus, the two parties should enter the deriv…
Securely share encrypted data for machine learning training.
Market incentivizes parties to share high-quality data for collaborative machine learning tasks.
Multi-party machine learning leaks global dataset properties even with black-box access.
In [1] Zawadoski introduces a banking network model in which the asset and counter-party risks are treated separately and the banks hedge their assets risks by appropriate OTC contracts. In his model, each bank has only two counter-party neighbors, a bank fails due to the counter-party risk only if at least one of its …
SecureGBM securely trains GBM models across two parties without revealing data.
Paper improves GBDT accuracy in federated learning.
This paper examines how voter concentration affects election outcomes in district-based systems.
Federated Learning is introduced to protect privacy by distributing training data into multiple parties. Each party trains its own model and a meta-model is constructed from the sub models. In this way the details of the data are not disclosed in between each party. In this paper we investigate the model interpretation…
Voluntary insurance contracts constitute a puzzle because they increase the expectation value of one party's wealth, whereas both parties must sign for such contracts to exist. Classically, the puzzle is resolved by introducing non-linear utility functions, which encode asymmetric risk preferences; or by assuming the p…
We introduce a class of financial contracts involving several parties by extending the notion of a two-person game option (see Kifer (2000)) to a contract in which an arbitrary number of parties is involved and each of them is allowed to make a wide array of decisions at any time, not restricted to simply `exercising t…
Unified approach to federated learning improves robustness and personalization.
A scalable protocol for federated averaging with privacy and correctness guarantees.
Federated learning can propagate bias from a few parties to all participants.
Private method measures nonlinear correlations between data hosted across two entities.
The paper proposes a model reward scheme for collaborative ML based on Shapley value and information gain.
Study tackles RLHF with diverse human feedback, showing limitations and proposing a meta-learning approach.
Back cover text: Megaprojects and Risk provides the first detailed examination of the phenomenon of megaprojects. It is a fascinating account of how the promoters of multibillion-dollar megaprojects systematically and self-servingly misinform parliaments, the public and the media in order to get projects approved and b…
In this work, we demonstrate universal multi-party poisoning attacks that adapt and apply to any multi-party learning process with arbitrary interaction pattern between the parties. More generally, we introduce and study -poisoning attacks in which an adversary controls of the parties, and for each cor…
The paper uses Black-Scholes model to analyze political support and coalition agreements.
In this paper, we have studied the pricing of a continuously collateralized CDS. We have made use of the "survival measure" to derive the pricing formula in a straightforward way. As a result, we have found that there exists irremovable trace of the counter party as well as the investor in the price of CDS through thei…
A framework for collaborative learning reduces communication rounds.
A new framework for federated learning tackles challenges with horizontally partitioned labels and stragglers.
Privacy-preserving eye tracking framework using synthetic images.
The current standalone deep learning framework tends to result in overfitting and low utility. This problem can be addressed by either a centralized framework that deploys a central server to train a global model on the joint data from all parties, or a distributed framework that leverages a parameter server to aggrega…
Secure neural network inference on untrusted platforms using holographic reduced representations.
This paper tackles bias in federated learning without compromising data privacy.
Paper tackles privacy-preserving distributed learning with ADMM.
Privacy is crucial in many applications of machine learning. Legal, ethical and societal issues restrict the sharing of sensitive data making it difficult to learn from datasets that are partitioned between many parties. One important instance of such a distributed setting arises when information about each record in t…
Improved privacy-preserving summation protocol with fewer messages.
Unlike other industries in which intellectual property is patentable, the financial industry relies on trade secrecy to protect its business processes and methods, which can obscure critical financial risk exposures from regulators and the public. We develop methods for sharing and aggregating such risk exposures that …
The paper proposes a fair and private decentralized deep learning framework.