DeepMove learns place representations from large movement data.
problem Lack of movement context in traditional place representations.
method Directly models movements between places using deep learning.
result DeepMove outperforms state-of-the-art methods in place categorization and clustering.
City2City translates place representations across cities using language translation techniques.
problem Lack of inter-city perspective in place representations from mobility data.
method Applied unsupervised machine language translation methods to translate place representations across different cities.
result Successfully translated place representations from one city to another, validated using landuse data.
The hippocampal network approximates future locations using Nyström kernel approximations.
problem Learning neural representations for future locations under transition distributions.
method Formally derived neural network based on Nyström kernel approximations.
result The network successfully approximates transition distributions and yields sparse, localized receptive fields.
Model place cells as spatial embeddings for efficient path planning and cognitive map construction.
problem Encoding spatial navigation in the hippocampus.
method Model place cells using spectral decomposition of multi-step random walk transition kernels, inducing sparsity and adjacency.
result Place cells encode spatial information through non-negativity and inner-product structure, forming a cognitive map.
Method discovers user habits from mobile data.
problem Understanding human mobility patterns and habits.
method Density-based clustering for spatio-temporal data and Gaussian Mixture Model (GMM).
result Many unique habits were identified from the datasets.
Framework learns item representations from text data for complementary and similar items.
problem Generating accurate complementary item recommendations from textual data.
method Quadruplet network learning framework for latent space representation of items.
result Items are placed closer together in latent space for similar and complementary items compared to non-complementary items.
Anosov representations of word hyperbolic groups into higher-rank semisimple Lie groups are representations with finite kernel and discrete image that have strong analogies with convex cocompact representations into rank-one Lie groups. However, the most naive analogy fails: generically, Anosov representations do not a…
Study uses contrastive learning to analyze market order behavior.
problem Understanding diverse market order behaviors.
method Self-supervised learning with triplet loss for order representation.
result Identified distinct behavior types using K-means clustering.
Space2Vec learns multi-scale spatial representations from grid cell insights.
problem Encoding spatial features with varying scales from GIS data.
method Proposes Space2Vec, a multi-scale representation learning model using grid cell insights.
result Space2Vec outperforms baselines in predicting POI types and image classification with geo-locations.
Deep learning improves sparse representation for better classification.
problem Improving classification accuracy using sparse representation.
method A transductive deep learning network combining convolutional autoencoder and fully-connected layers.
result The proposed network achieves better classification results than state-of-the-art SRC methods.
Geometric approach connects Burau representation to sphere metrics, identifying kernels.
problem Faithfulness of the Burau representation for the 4-strand case.
method Geometric and orbifold theory.
result Identifies the kernel of the Burau representation for some cases.
Paper simplifies ANN structure into a functional form.
problem Current ANN structure is complex and difficult to analyze.
method Uses activation integral concept to represent ANN structure as a function.
result Simplified mathematical representation of ANN structure.
We present a universal knot polynomials for 2- and 3-strand torus knots in adjoint representation, by universalization of appropriate Rosso-Jones formula. According to universality, these polynomials coincide with adjoined colored HOMFLY and Kauffman polynomials at SL and SO/Sp lines on Vogel's plane, and give their ex…
RoBERTa model detects counterfactual statements in text.
problem Detecting and extracting counterfactual statements from text.
method Used RoBERTa language representation model for both subtasks.
result RoBERTa achieved top performance in both subtasks at SemEval-2020.
A knot complement admits a pseudo-hyperbolic structure by solving Thurston's gluing equations for an octahedral decomposition. It is known that a solution to these equations can be described in terms of region variables, also called w-variables. In this paper, we consider the case when pinched octahedra appear as a b…
Paper develops a framework for learning interpretable representations of sequential decision behavior.
problem Obtaining a transparent description of existing behavior.
method Inverse decision modeling framework, formalizing both forward and inverse problems.
result Learning interpretable representations of behavior, including suboptimal actions, biased beliefs, and imperfect knowledge.
Automatic Music Transcription (AMT) is one of the oldest and most well-studied problems in the field of music information retrieval. Within this challenging research field, onset detection and instrument recognition take important places in transcription systems, as they respectively help to determine exact onset times…
Study uses trajectory embedding to measure place function similarity at fine spatial granularity.
problem Measuring place function similarity at fine spatial granularity.
method Trajectory embedding to reduce dimensions and measure similarity of place functions.
result Embedding similarity can be a metric proxy for place functions at fine spatial granularity.
Proposes a method to learn invariant representations for interpretability and fairness.
problem Learning invariant representations to achieve interpretability in algorithmic fairness.
method Adversarially trained model with null-sampling procedure to produce invariant representations in the data domain.
result Shows effectiveness on image and tabular datasets.
I will explain my joint paper `Instantons moduli spaces and W-algebras' with A.Braverman, M.Finkelberg, arXiv:1406.2381. I will concentrate on the geometric part, that is a study of perverse sheaves on instanton moduli spaces. I place a particular emphasize on the hyperbolic restriction functor and stable envelop, whic…
Factorization of the differential expansion coefficients for HOMFLY-PT polynomials of double braids, discovered in arXiv:1606.06015 in the case of rectangular representations R, is extended to the first non-rectangular representations R=[2,1] and R=[3,1]. This increases chances that such factorization will take p…
Motivated by the study of ribbon knots we explore symmetric unions, a beautiful construction introduced by Kinoshita and Terasaka 50 years ago. It is easy to see that every symmetric union represents a ribbon knot, but the converse is still an open problem. Besides existence it is natural to consider the question of un…
Improved Q-learning for multi-agent reinforcement learning by weighting joint action values.
problem QMIX restricts Q-values to monotonic mixtures, limiting complex value functions. method Introduced weighted projection to recover optimal policies, improving performance.
result CW QMIX and OW QMIX outperform baseline QMIX on multi-agent tasks.
A central problem to understanding intelligence is the concept of generalisation. This allows previously learnt structure to be exploited to solve tasks in novel situations differing in their particularities. We take inspiration from neuroscience, specifically the hippocampal-entorhinal system known to be important for…
Inspired by the paper on quantum knots and knot mosaics [23] and grid diagrams (or arc presentations), used extensively in the computations of Heegaard-Floer knot homology [2,3,7,24], we construct the more concise representation of knot mosaics and grid diagrams via mirror-curves. Tame knot theory is equivalent to knot…
If M is a hyperbolic once-punctured torus bundle over the circle, then the trace field of M has no real places.
Dual representation and properties of expectile-based expected shortfall studied.
problem Studying the expectile-based expected shortfall as a risk measure.
method Provided dual representation in terms of Bochner integral, showed boundedness properties, and computed for selected distributions.
result Explicit dual representation and boundedness properties of expectile-based expected shortfall.
Explains how Higgs bundles help study Fuchsian representations on surfaces.
problem Understanding components of character varieties for Fuchsian representations.
method Theory of Higgs bundles, focusing on real groups and their subtleties.
result Characterizes deformation spaces of Fuchsian representations using Higgs bundles.
In this paper I develop a new computational method for pricing path dependent options. Using the path integral representation of the option price, I show that in general it is possible to perform analytically a partial averaging over the underlying risk-neutral diffusion process. This result greatly eases the computati…
L2P predicts heavy-tailed outcomes by placing new instances among known ones.
problem Predicting heavy-tailed outcomes (e.g., best-sellers) with under-prediction by existing methods.
method Learning to Place (L2P) learns pairwise preferences and places new instances to estimate outcomes.
result L2P outperforms existing methods in accuracy and reproducing heavy-tailed distributions.
A new model predicts race places using changeover-times and log-normal distributions.
problem Predicting race places in orienteering races.
method Fenton-Wilkinson Order Statistics model based on log-normal leg-times and changeover-times.
result The model accurately predicts race places with smaller root-mean-square-errors.
We introduce the Attentive Unsupervised Text (W)riter (AUTR), which is a word level generative model for natural language. It uses a recurrent neural network with a dynamic attention and canvas memory mechanism to iteratively construct sentences. By viewing the state of the memory at intermediate stages and where the m…
Our results complement D. Calegari's result that there are no hyperbolic once-punctured torus bundles over S1 with trace field having real place. We exhibit several infinite families of pairs (−χ,p) such that there exist hyperbolic surface bundles with over S1 with fiber having p punctures and Euler characte…
Study explores reinforcement learning in a complex game environment, analyzing rule inference and policy learning.
problem Learning optimal policies in environments with hidden rules.
method Investigated using the Game Of Hidden Rules (GOHR) environment, employing Feature-Centric and Object-Centric state representations with a Transformer-based A2C algorithm.
result Transformer-based A2C models outperform traditional methods in GOHR, demonstrating the effectiveness of representation strategies.
In-Place TTT enhances LLMs with dynamic parameter updates at inference time.
problem Static training limits LLMs from adapting to new information.
method In-Place TTT updates a subset of model parameters (fast weights) at inference time.
result In-Place TTT enables 4B-parameter models to outperform on tasks with up to 128k contexts.
Improved reconstruction performance in disentanglement challenge.
problem Learning disentangled representations from real-world data.
method Adopted FactorVAE and improved reconstruction performance.
result Achieved 1st place in the disentanglement challenge.
Zoetrope Genetic Programming improves symbolic regression performance.
problem Evolutionary symbolic regression for complex mathematical expressions.
method Zoetropic representation, repeated fusion operations, linear combination, crossover, mutation, selection.
result Zoetrope Genetic Programming achieves state-of-the-art performance and low computational time.
WiSE-ALE improves VAEs by learning a flexible aggregate posterior.
problem Learning compact latent representations from large datasets.
method Derives a new variational lower bound and uses it to place a prior on the entire dataset.
result WiSE-ALE achieves excellent reconstruction quality with a smooth, compact representation.
Period domains, the classifying spaces for (pure, polarized) Hodge structures, and more generally Mumford-Tate domains, arise as open GR--orbits in flag varieties G/P. We investigate Hodge--theoretic aspects of the geometry and representation theory associated with these flag varieties. In particular, w…
PMP extends GNNs to handle past states efficiently.
problem Efficient querying of data structures dependent on previous states.
method Persistent Message Passing (PMP) which persists past states through new nodes.
result Significantly outperforms GNNs in handling out-of-distribution data.
Paper proposes a graph network for EHR data that learns robust representations.
problem Learning robust representations for EHR data with implicit connections.
method Variationally regularized encoder-decoder graph network.
result Model outperforms existing methods in various EHR predictive tasks.
Defines smooth actions of a group on manifolds and vector spaces.
problem Representing the general linear group and its actions.
method Restricted functor of points and category theory.
result Smooth actions on Z2n-graded vector spaces and manifolds. Microsoft Research Asia won first place in 8 out of 11 WMT19 language directions.
problem Improving machine translation quality across multiple languages.
method Transformer, back translation, knowledge distillation, MADL, MASS, NAO, SCA.
result Demonstrated significant improvement in 8 out of 11 WMT19 language directions.
New method discourages models from using bias shortcuts for better generalization.
problem Training models on biased data can lead to poor generalization when bias shifts.
method Train a de-biased representation by encouraging it to differ from biased representations.
result Improved generalization across synthetic and real-world biases.
Using the L^2 norm of the Higgs field as a Morse function, we study the moduli spaces of U(p,q)-Higgs bundles over a Riemann surface. We require that the genus of the surface be at least two, but place no constraints on (p,q). A key step is the identification of the function's local minima as moduli spaces of holomorph…
Study identifies latent variables and causal relationships from multiple environments.
problem Identify latent variables and causal relationships from multiple environments.
method Proposes algorithm LiNGCReL for identifying causal graph up to surrounded-node ambiguity.
result Identifies latent variables up to surrounded-node ambiguity (SNA) in linear causal models.
New theory explains how Normalizing Flows represent data.
problem Lack of theoretical foundation in Normalizing Flows.
method Linear systems theory applied to Normalizing Flows.
result Optimal flows learn to represent local covariance.
Let G be an almost simple, simply connected algebraic group defined over a number field k, and let S be a finite set of places of k including all infinite places. Let X be the product over v∈S of the symmetric spaces associated to G(kv), when v is an infinite place, and the Bruhat-Tits buildings ass…