Explains deep neural networks using new interpretation techniques.
problem Interpreting and understanding deep neural networks.
method Introduces new techniques for interpretation and practical applications.
result Efficient use of interpretation techniques on real data.
ICML workshop on making machine learning models more understandable.
problem Making machine learning models more understandable to humans.
method Various presentations and discussions on interpretability techniques.
result Improved methods for explaining machine learning models.
Symposium on making machine learning models more understandable.
problem Making machine learning models more understandable.
method Not specified in the abstract.
result Not specified in the abstract.
State-of-the-art speaker recognition relays on models that need a large amount of training data. This models are successful in tasks like NIST SRE because there is sufficient data available. However, in real applications, we usually do not have so much data and, in many cases, the speaker labels are unknown. We present…
NIPS workshop focuses on ML for developing countries.
problem Addressing machine learning challenges in developing nations.
method Not specified in the abstract.
result Not specified in the abstract.
NetRCA algorithm locates network faults by analyzing derived features and leveraging unlabeled data.
problem Locating the true root cause of network faults is challenging due to complex architectures and limited labeled data.
method NetRCA algorithm extracts derived features, generates new training data, and combines multiple models to enhance performance.
result NetRCA outperforms existing methods in fault cause localization on real-world data.
Convolutional neural networks win SemEval-2017 for scientific relation extraction.
problem Extracting relations between scientific concepts from scholarly articles.
method Convolutional neural network model for relation extraction.
result Ranked first in SemEval-2017 Task 10 for relation extraction in scientific articles.
Tangent Works won GEFCom 2017 using automatic model building.
problem Forecasting time series with historical temperature shuffling.
method Automatic model building using Tangent Information Modeller (TIM) with historical temperature shuffling and decision on trend variable.
result Automated model building setup won the competition.
Study shows changes in information sharing between Bitcoin markets during 2017 crash.
problem Understanding information dynamics in Bitcoin markets during the 2017 crash.
method Analysis of high-frequency market-microstructure observables using information theoretic measures.
result Temporal changes in information sharing across markets, including predictability, memory, and synchronous coupling.
Amobee's system won 3rd place in Twitter sentiment classification.
problem Sentiment detection on Twitter using deep learning.
method RNN models trained on a sentiment treebank, combined with classifiers.
result 3rd place in SemEval 2017 task 4, 5-label classification.
Y. Nikonorov completes a proof in a geometry paper.
problem Completing a proof in a geometry paper.
method Completing an argument from a previous proof.
result Proof of Theorem 2.5 in JGA 27 (2017) is now complete.
ES and FD gradients converge as optimization dimension grows.
problem Understanding the relationship between Evolution Strategies and Finite Differences gradients.
method Analyzing the convergence of gradients as the optimization dimension increases.
result ES and FD gradients converge as the dimension of the vector under optimization increases.
Survey of open problems in finite-dimensional integrable systems.
problem Open problems in finite-dimensional integrable systems.
method None specified; survey of existing open problems.
result Many open problems were identified from a conference.
Recently, it was demonstrated in [CS2012,CS2013] that the robustness of the classical Non-Local Means (NLM) algorithm [BCM2005] can be improved by incorporating ℓp(0<p≤2) regression into the NLM framework. This general optimization framework, called Non-Local Patch Regression (NLPR), contains NLM as a spe…
Two algorithms find local minima faster in finite-sum and general stochastic optimization.
problem Finding local minima in finite-sum and general stochastic nonconvex optimization.
method Stochastic Nested Variance Reduction (SNVRG) + Neon2.
result Achieves better gradient complexity for convergence to (ε,εH)-second-order stationary points. In compressed sensing problems, ℓ1 minimization or Basis Pursuit was known to have the best provable phase transition performance of recoverable sparsity among polynomial-time algorithms. It is of great theoretical and practical interest to find alternative polynomial-time algorithms which perform better than $\e…
A new system detects audio replay attacks with high accuracy.
problem Detecting and preventing audio replay attacks in speaker verification systems.
method Proposes Attentive Filtering Network combining attention-based filtering and ResNet classifier.
result Achieves EER of 8.99% on ASVspoof 2017 Version 2.0 dataset.
Stable ResNet stabilizes gradients in deep networks.
problem Gradient vanishing and exploding in deep ResNet architectures.
method Introducing Stable ResNet architectures with gradient stabilization and infinite depth expressivity.
result Stable ResNet maintains gradient stability and expressivity in deep networks.
Improved neural network robustness against adversarial attacks.
problem Adversarial attacks on neural networks.
method Adversarial-trained Bayesian Neural Network (Adv-BNN).
result State-of-the-art performance improvement under strong attacks.
Forecast predicts US recession in 2017, global economic slowdown, and eventual growth.
problem Short-term economic forecast and potential recession in developed countries.
method Analysis of log-periodic oscillations in DJIA dynamics and historical economic cycles.
result Predicts a recession in the second half of 2017 for developed countries.
Study quantifies reproducibility of machine learning papers.
problem Lack of empirical reproducibility metrics in machine learning.
method Manual implementation of 255 papers from 1984-2017, analyzing features and results.
result Manual implementation revealed discrepancies between papers and their descriptions.
EWC uses quadratic penalties that may double-count earlier task data.
problem Catastrophic forgetting in neural networks.
method Extended derivation of EWC with multiple tasks.
result Quadratic penalties in EWC might double-count earlier task data.
Directly analyzes SGLD hitting times for stationary points, providing tighter bounds.
problem Analyzing the hitting time of SGLD to stationary points.
method Direct analysis using linear algebra and probability theory, avoiding complex Cheeger's constant bounds.
result Tighter bounds on hitting times compared to previous work, showing dimension-independent behavior under suitable conditions.
New estimator stabilizes higher-order influence functions for stable statistical inference.
problem Numerical instability in estimating inverse population Gram matrix.
method Proposes a new stabilized higher-order estimator without sample splitting.
result Stabilized estimator exhibits more stable performance and similar statistical guarantees.
Paper compares different spoofing detection methods for speech verification.
problem Detecting audio replay attacks in speech verification systems.
method GMM based methods, high level features extraction with simple classifier, deep learning frameworks.
result Deep learning approaches are efficient in changing acoustic conditions.
New method calibrates rough stochastic volatility models quickly.
problem Calibrating rough stochastic volatility models is expensive and time-consuming.
method Combines Levenberg-Marquardt with neural networks for fast calibration.
result Neural network approximates implied volatility map efficiently.
Deep ResNets with single-neuron hidden layers can approximate any function.
problem The challenge of universal approximation by deep neural networks.
method A ResNet architecture with one neuron per hidden layer in each module.
result ResNet with one-neuron hidden layers is a universal approximator.
New estimator stabilizes higher-order influence functions for bilinear forms.
problem Stability issues in estimating bilinear forms using higher-order influence functions.
method Proposes a new stabilized higher-order estimator for a class of bilinear forms without sample splitting.
result New estimator exhibits more stable finite-sample performance compared to the empirical higher-order estimator.
Hard to estimate L2-accurate scores without strong assumptions.
problem Estimating the score of unknown data distributions accurately.
method Reduction to generating samples and leveraging lattice-based cryptography hardness.
result Score estimation is computationally hard even with polynomial sample complexity.
Neural networks model future values in finance.
problem Modeling future values of financial portfolios.
method Deep learning with neural networks to parameterize future values, optimizing parameters.
result Obtained expected positive/negative exposures for specific financial products.
State-of-the-art Twitter sentiment analysis using CNNs and LSTMs.
problem Improving Twitter sentiment classification accuracy.
method Pre-trained word embeddings, distant supervision, fine-tuning, ensemble of CNNs and LSTMs.
result First rank on all five English subtasks of SemEval-2017.
The Dynamic Pricing Challenge revealed varying algorithm performance across different market dynamics.
problem Complexity of pricing and learning in competitive markets.
method Participants submitted pricing and demand learning algorithms for numerical performance analysis in simulated environments.
result Algorithm performance varies significantly across different market dynamics.
New insights into neural network initialization and activation functions improve deep learning performance.
problem Inappropriate initialization and activation function selection can hinder deep neural network training.
method Theoretical analysis and quantitative results on weight initialization and activation functions.
result Random initialization at the edge of chaos improves information propagation in deep neural networks.
Iterated Amplification uses subproblem solutions to build training signals for complex tasks.
problem Learning complex tasks when humans can't directly evaluate performance.
method Progressively builds training signal by combining solutions to easier subproblems.
result Efficiently learns complex behaviors in algorithmic environments.
New model closes gap in understanding equivariant set functions.
problem Understanding universality of equivariant set functions.
method Proves PointNet not equivariant universal and introduces PointNetST.
result PointNetST is the simplest permutation equivariant universal model.
New method for precise option pricing in stochastic volatility models.
problem Analyzing large classes of stochastic volatility models for robust option pricing.
method Theory of regularity structures and Laplace method on the space of models.
result Precise asymptotics for European options in rough volatility models.
New method optimizes convex problems across smooth and non-smooth settings.
problem Convex optimization in various settings (smooth, non-smooth, stochastic).
method Adaptive learning rate with importance weights and linearly coupled sequences.
result Simultaneous accelerated and standard convergence rates across settings.
Lecture notes on advanced homology theories.
problem Finding periodic orbits in complex systems.
method Floer and Rabinowitz-Floer homology.
result Advanced mathematical tools for studying periodic orbits.
Biography of mathematician Herbert Busemann.
problem N/A
method N/A
result N/A
This work generalizes a formula linking Seiberg-Witten prepotential and topological recursion.
problem Analyzing the relationship between Seiberg-Witten curves and topological recursion.
method Analytical approach using Seiberg-Witten family of curves.
result A generalized formula relating Seiberg-Witten prepotential to the genus zero part of topological recursion on a Seiberg-Witten curve.
Shared task on machine translation using weak user feedback.
problem Learning machine translation from unreliable user feedback.
method Bandit learning approach using real-valued quality estimates.
result Various machine translation architectures and protocols were evaluated.
Winning solution for predicting player churn in a video game.
problem Predicting when players will stop playing a game.
method Long Short-Term Memory (LSTM) approach and conditional inference survival ensemble model.
result Models accurately predicted player churn and were robust to changing business models.
Study on distributions of realized and implied volatility, using Generalized Beta distribution.
problem Understanding the differences and relationships between realized and implied volatility distributions.
method Used Generalized Beta distribution to fit distributions of realized variance and implied volatility (VIX, VXO). Analyzed differences and correlations.
result Generalized Beta distribution provides the best fit for realized variance but not for implied volatility indices (VIX, VXO).
LR models are shown to represent and be represented by LG processes, with key properties facilitating interest rate consistency and long-term risk factorization.
problem Understanding the relationship between linearity-generating and linear-rational models.
method Comparing and contrasting LG and LR models, showing mutual representation and identifying key properties.
result LR models can represent and be represented by LG processes, with specific properties facilitating interest rate consistency and long-term risk factorization.
Law of iterated logarithm derived from betting strategy.
problem Deriving the law of the iterated logarithm.
method Using a betting strategy's wealth guarantee.
result Law of the iterated logarithm established.
The paper extends ERP framework to non-monotonic payoffs and short selling bans.
problem Valuation of contingent claims with short selling bans under ERP framework.
method Unified framework for ERP pricing, extending to non-monotonic payoffs, and comparing with Black-Scholes.
result Equal-risk prices differ from Black-Scholes prices under short selling bans.
Supermixed labyrinth fractals extend mixed fractals by using multiple patterns.
problem Extending labyrinth fractals to use multiple patterns.
method Iterative construction using multiple labyrinth patterns.
result Sufficient condition for infinite length of arcs in supermixed labyrinth fractals.
The DAO Report led to a significant shift of ICO activity to Europe.
problem The impact of U.S. regulatory changes on global ICO activity.
method Analysis of a global dataset of ICOs from 2014 to 2021, focusing on the DAO Report's effects.
result A substantial and persistent reallocation of ICO activity to Europe following the DAO Report.