Paper proposes SAN and SN for zero-shot sketch-based image retrieval.
problem Handling unseen classes in sketch-based image retrieval.
method Generative approach using Stacked Adversarial Network (SAN) and Siamese Network (SN).
result Significant improvement in standard and generalized ZSL settings.
New method reduces linear regret in high-dimensional bandit problems.
problem Heavy spectral tails in streaming matrices lead to linear regret in sketch-based linear bandits.
method Dyadic Block Sketching, a multi-scale matrix sketching approach.
result Achieves sublinear regret bounds without prior knowledge of streaming matrix properties.
Sketch-based approach detects community events in evolving networks.
problem Community detection in time-varying networks.
method Maintains a small sketch graph to capture essential community structure.
result Efficiently identifies six key community events during network evolution.
We present a probabilistic model for Sketch-Based Image Retrieval (SBIR) where, at retrieval time, we are given sketches from novel classes, that were not present at training time. Existing SBIR methods, most of which rely on learning class-wise correspondences between sketches and images, typically work well only for …
Global watermark for diffusion language models decouples detection from local contexts.
problem Watermarking in diffusion language models is challenging due to joint sampling of distributions over many unresolved positions.
method Proposes a global vector-valued sketch representation to control watermarking in masked diffusion language models.
result The method decouples detection from local contexts, resulting in an order-agnostic statistic and robustness.
We derive optimal statistical and computational complexity bounds for exp-concave stochastic minimization in terms of the effective dimension. For common eigendecay patterns of the population covariance matrix, this quantity is significantly smaller than the ambient dimension. Our results reveal interesting connections…
Model predicts next destination for users based on past trips and features.
problem Predicting the next destination in multi-destination trips.
method Used Cleora for city graph embedding and EMDE for prediction.
result Achieved 2nd place in Booking Data Challenge.
Communication and privacy are two critical concerns in distributed learning. Many existing works treat these concerns separately. In this work, we argue that a natural connection exists between methods for communication reduction and privacy preservation in the context of distributed machine learning. In particular, we…
Fisher discriminant analysis (FDA) is a widely used method for classification and dimensionality reduction. When the number of predictor variables greatly exceeds the number of observations, one of the alternatives for conventional FDA is regularized Fisher discriminant analysis (RFDA). In this paper, we present a simp…
Skeinformer accelerates self-attention for long sequences with linear complexity.
problem Efficiency of Transformer models in processing long sequences.
method Matrix sketching and column sampling to reduce quadratic complexity to linear.
result Skeinformer outperforms alternatives with smaller time/space footprint.
This paper studies how to sketch element-wise functions of low-rank matrices. Formally, given low-rank matrix A = [Aij] and scalar non-linear function f, we aim for finding an approximated low-rank representation of the (possibly high-rank) matrix [f(Aij)]. To this end, we propose an efficient sketching-based algorithm…
Paper proposes Nyström sketches for better adaptive compressive learning.
problem Improving adaptability of sketching for compressive learning.
method Data-dependent Nyström approximation for mean embedding.
result Excess risk can be controlled with geometric assumption.
Detecting emergence of a low-rank signal from high-dimensional data is an important problem arising from many applications such as camera surveillance and swarm monitoring using sensors. We consider a procedure based on the largest eigenvalue of the sample covariance matrix over a sliding window to detect the change. T…
In this paper, we develop a novel procedure for low-rank tensor regression, namely \emph{\underline{I}mportance \underline{S}ketching \underline{L}ow-rank \underline{E}stimation for \underline{T}ensors} (ISLET). The central idea behind ISLET is \emph{importance sketching}, i.e., carefully designed sketches based on bot…
Sketching accelerates structured prediction methods for large datasets.
problem Scaling surrogate kernel methods for large datasets.
method Sketching approximations applied to input and output feature maps.
result Achieves close-to-optimal rates with reduced sketch size.
In response to growing concerns about user privacy, federated learning has emerged as a promising tool to train statistical models over networks of devices while keeping data localized. Federated learning methods run training tasks directly on user devices and do not share the raw user data with third parties. However,…
We improve prediction risk estimation for large datasets using sketching and ridge regression.
problem Estimating prediction risks for large datasets efficiently and accurately.
method Random matrix theory, generalized cross validation, sketched ridge regression ensembles, and ensemble trick.
result Consistent risk estimation and prediction intervals for large-scale datasets.
SAPPHIRE tackles ill-conditioned rERM problems with faster convergence.
problem Ill-conditioned objectives and non-smooth regularizers in rERM.
method Sketch-based preconditioning and scaled proximal mapping.
result Achieves condition-number-free linear convergence.
S3Attention improves long sequence attention with smoothed skeleton sketching.
problem Quadratic complexity of vanilla Attention makes it unsuitable for long sequence tasks.
method S3Attention uses smoothing and matrix sketching to balance information preservation and computation. result S3Attention significantly outperforms vanilla Attention and other Attention variants. Sketch-GNN reduces GNN training time and memory usage to sublinear scales.
problem Training GNNs on large graphs is computationally expensive and memory-intensive.
method Develops a sketch-based algorithm that trains GNNs on compact sketches of graph adjacency and node embeddings.
result Training time and memory usage grow sublinearly with respect to graph size.
Improved privacy-preserving linear regression via iterative Hessian mixing.
problem Differentially private linear regression with improved accuracy and efficiency.
method Iterative Hessian Mixing (IHM) for differentially private ordinary least squares (DP-OLS).
result IHM provides better utility guarantees and outperforms AdaSSP in empirical evaluations.
Efficiently applies NTK to large-scale datasets using random features.
problem Computational limitations of kernel methods for large-scale datasets.
method Proposes a sketching-based algorithm combining random features of arc-cosine kernels to construct an efficient feature map of the NTK.
result Achieves comparable error bounds to exact kernel methods but with significantly reduced feature dimensionality.
Gaussian processes (GP) are a well studied Bayesian approach for the optimization of black-box functions. Despite their effectiveness in simple problems, GP-based algorithms hardly scale to high-dimensional functions, as their per-iteration time and space cost is at least quadratic in the number of dimensions d and i…
Proposes a new method for optimizing large-scale models using Nyström approximation of the Hessian.
problem Optimizing non-convex functions like deep learning models using second-order methods.
method Nyström-approximated curvature for stochastic optimization of large-scale empirical risk minimization.
result The proposed method achieves performance competitive with state-of-the-art first-order and stochastic quasi-Newton methods.
New decoder improves robustness of compressive clustering.
problem Designing robust decoders for compressive clustering.
method Inspired by mean shift, proposes a new decoder.
result Significantly improves recovery of clusters from smaller sketches.
T-EMDE bridges the heterogeneity gap between image and text modalities.
problem Finding similarities between image and text modalities with non-related feature spaces.
method Inspired by EMDE, T-EMDE uses sketches for multimodal operations, avoiding self-attention's quadratic complexity.
result T-EMDE achieves state-of-the-art results and reduces model latency.
Optimal hashing embeddings reduce linear least squares solving time.
problem Efficiently solving large-scale linear least squares problems.
method Optimal hashing sketching matrices for linear least squares.
result Ski-LLS outperforms state-of-the-art solvers on various problem types.
Randomized SVD shows phase transitions in noisy data.
problem Noise sensitivity of randomized SVD in large rank matrices.
method Analyzed R-SVD under low-rank signal plus noise model.
result R-SVD exhibits BBP-like phase transition with outliers above detectability threshold.