Beam search improves feature selection for better model performance.
problem Improving feature selection for better model performance.
method Proposed beam search as a generalization of forward selection for feature selection.
result Beam search can outperform forward selection, especially with correlated features.
Optimizes tree models for better beam search performance.
problem Beam search causes retrieval performance deterioration in tree models.
method Develops Bayes optimality and calibration under beam search, proposes a novel algorithm for optimal tree model learning.
result Eliminates the training-testing discrepancy in tree models.
Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence at train time, and therefore do not explicitly learn how to use the beam. We develop an unifying meta-algorithm for learning beam search policies using imitation learning.…
Attention-based encoder decoder network uses a left-to-right beam search algorithm in the inference step. The current beam search expands hypotheses and traverses the expanded hypotheses at the next time step. This traversal is implemented using a for-loop program in general, and it leads to speed down of the recogniti…
Improved neural keyphrase generation by beam search with reward functions.
problem Sequence length bias and beam diversity issues in neural keyphrase generation.
method Beam search decoding strategy with word-level and ngram-level reward functions.
result Significant improvement in generating diverse and accurate keyphrases.
Beam search improves UQ in LLMs by reducing duplicates and variance.
problem Peaked distributions in multinomial sampling lead to duplicates and high variance in uncertainty estimates.
method Employ beam search to generate candidates for consistency-based UQ, providing a theoretical lower bound and empirical evaluation.
result Beam search achieves smaller error than multinomial sampling, leading to state-of-the-art UQ performance.
Paper improves EEG-based speech recognition using CTC and beam search.
problem Improving continuous speech recognition from EEG signals.
method Implemented CTC-based ASR system, initialized weights, used external language model, studied articulatory feature prediction.
result Enhanced performance of EEG-based speech recognition systems.
Study improves calibration of NMT models, especially EOS and attention uncertainty.
problem Improper functioning of beam-search inference due to miscalibrated NMT models.
method Design and apply recalibration methods based on EOS and attention uncertainty signals.
result Improved accuracy and better sequence-level calibration of NMT models.
A new method samples sequences without replacement using Gumbel-Top-k trick.
problem Sampling sequences without replacement from large domains efficiently.
method Gumbel-Top-k trick applied to Stochastic Beam Search.
result Efficient sampling with linear model evaluations in k. Bardo Composer generates tabletop RPG music based on player speech.
problem Creating immersive background music for tabletop RPGs.
method Speech recognition, emotion classification, and music generation using a novel beam search algorithm.
result Generated music pieces can be accurately identified by human subjects as conveying the intended emotion.
We introduce a new sampling method for large language models that balances diversity and parallelism.
problem Balancing diversity and parallelism in decoding for large language models.
method Arithmetic sampling framework compatible with various sampling variations.
result Improves estimation of expected BLEU score reward and reduces the gap with beam search.
New method improves text generation by assigning lower probability to repetitive sequences.
problem Dull and repetitive text generated by standard likelihood training.
method Unlikelihood training, which forces unlikely generations to be assigned lower probability.
result Unlikelihood training produces less repetitive, less dull text compared to standard techniques.
Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work…
Federated LIDAR aided beam selection reduces mmWave beam search overhead.
problem Efficient link configuration in mmWave communication systems with reduced beam search overhead.
method Federated learning of LIDAR data to train a shared neural network for beam selection.
result Proposed method significantly outperforms previous works in performance and complexity.
This study investigates global normalization in neural models, showing its effectiveness in search-aware training.
problem Theoretical equivalence of global and local normalization in high-capacity models, practical advantage unclear.
method Continuous relaxation of beam search for training globally normalized recurrent sequence models.
result Globally normalized models are more effective than locally normalized ones in inexact search.
OKRidge solves sparse ridge regression problems for nonlinear systems.
problem Identifying sparse governing equations for nonlinear dynamical systems.
method OKRidge algorithm using saddle point formulation and ADMM-based approach with efficient proximal operators.
result OKRidge achieves provable optimality with significantly faster run times than Gurobi.
New seq2seq model can copy entire spans, outperforming simpler models in editing tasks.
problem Editing documents or source code using seq2seq models with explicit token copying.
method Extended seq2seq model capable of copying entire input spans to output in one step, new training and inference methods.
result New model consistently outperforms simpler baselines in editing tasks of natural language and source code.
A neural program synthesis method with iterative fix operations.
problem Creating correct programs from input-output examples.
method Combines encoder-decoder synthesis with a differentiable fixer.
result Improves synthesis accuracy by reducing discrepancies between outputs and desired outputs.
Bayesian method adapts to unknown distribution shifts in online learning.
problem Online learning with unknown and irregular distribution shifts.
method Bayesian inference with change-point detection and beam search.
result Improves adaptation to new data distributions over state-of-the-art methods.
Adaptive contrastive search improves text generation quality and diversity.
problem Decoding high-quality text from language model outputs.
method Adaptive contrastive search incorporating uncertainty-guided degeneration penalty.
result Enhanced text generation quality and diversity across different models and datasets.
AutoCross automatically generates feature interactions for tabular data.
problem Capturing interactions among categorical features in tabular data.
method Beam search in a tree-structured space, successive mini-batch gradient descent, multi-granularity discretization.
result Significantly enhances performance of linear and deep models.
This research explores various sampling methods and probability distributions for hard alignment in sequence-to-sequence TTS synthesis.
problem Improving alignment accuracy in sequence-to-sequence text-to-speech synthesis.
method Investigated various sampling methods (greedy, beam, random) and probability distributions (Bernoulli, Concrete) for hard alignment.
result Deterministic search is more preferable than stochastic search for natural alignment transition.
New model uses pretrained biochemical language models to generate drug compounds.
problem Developing novel compounds targeting specific proteins.
method Exploits pretrained language models to initialize and fine-tune targeted molecule generation models.
result Warm-started models outperform baseline models, with one-stage strategy showing better generalization.
A new framework predicts hidden Markov model regimes online.
problem Efficiently identify hidden Markov model regimes in streaming data.
method Develops a predictive-first optimisation framework for streaming HMMs, approximating the full posterior predictive distribution.
result The method provides competitive prequential performance compared to Online EM and Sequential Monte Carlo.
Proposes a method to generate diverse translations by conditioning on target domain.
problem NMT models lack diversity in translations, even with search algorithms.
method Condition the decoder on a latent variable representing target domain, generated by a target encoder.
result Generated diverse translations without affecting performance or training time.
A new score SiNNE improves OAM efficiency and accuracy.
problem Comparing outlier scores across subspaces of different dimensions.
method Introducing SiNNE, a new score independent of subspace dimensionality.
result SiNNE produces better or at least as good results as existing scores and significantly improves runtime.
We present a supervised neural network model for polyphonic piano music transcription. The architecture of the proposed model is analogous to speech recognition systems and comprises an acoustic model and a music language model. The acoustic model is a neural network used for estimating the probabilities of pitches in …
Deep Retrieval learns a retrievable structure for efficient large-scale recommendations.
problem Efficiently retrieving top relevant candidates in large-scale recommendation systems.
method Deep Retrieval learns a retrievable structure directly from user-item interaction data, encoding candidates into a discrete latent space and optimizing a model to maximize accuracy.
result Deep Retrieval achieves almost the same accuracy as brute-force baseline and significantly outperforms ANN baselines in a live production system.
We stabilize the activations of Recurrent Neural Networks (RNNs) by penalizing the squared distance between successive hidden states' norms. This penalty term is an effective regularizer for RNNs including LSTMs and IRNNs, improving performance on character-level language modeling and phoneme recognition, and outperfor…
Recent advances in conditional recurrent language modelling have mainly focused on network architectures (e.g., attention mechanism), learning algorithms (e.g., scheduled sampling and sequence-level training) and novel applications (e.g., image/video description generation, speech recognition, etc.) On the other hand, …
Improves music composition with user-defined constraints using continuous time models.
problem Combining sequence models with user-defined constraints in continuous time.
method Introduces a novel particle filter scheme for continuous time point processes.
result The particle filter scheme yields superior results in a human listening test.
This work proposes an efficient autoregressive model for text generation.
problem The challenge of generating high-quality text with autoregressive models.
method Introduces a cascaded decoding approach using Markov transformers to achieve sub-linear parallel time generation.
result Shows competitive accuracy/speed tradeoff compared to existing methods on five machine translation datasets.
New deep learning method solves TSP faster and more efficiently.
problem Approximately solving the Travelling Salesman Problem on 2D Euclidean graphs.
method Uses Graph Convolutional Networks for efficient TSP graph representations and non-autoregressive beam search.
result Significantly reduces optimality gap for large problem instances.
Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in performance compared to non-streaming models such as Listen, Attend and Spell (…
Modeling human language learning with multi-checkpoint machine translation.
problem Improving machine translation quality for language education.
method Ensemble of multi-checkpoints from a single model, sampling n-best sequences.
result Achieved 37.57 macro F1 score, outperforming baseline.
Finding the diameter of a dataset in multidimensional Euclidean space is a well-established problem, with well-known algorithms. However, most of the algorithms found in the literature do not scale well with large values of data dimension, so the time complexity grows exponentially in most cases, which makes these algo…
This paper proposes a method for multi-class classification problems, where the number of classes K is large. The method, referred to as Candidates vs. Noises Estimation (CANE), selects a small subset of candidate classes and samples the remaining classes. We show that CANE is always consistent and computationally effi…
In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing language generation techniques are usually based on recurrent neural networks (RNNs). However, it is non-trivial to impose constraints on RNNs whil…
SED integrates synthesis, execution, and debugging for neural program synthesis.
problem Challenges in synthesizing complex programs that match specifications.
method SED combines synthesis, execution, and debugging to improve neural program generation.
result SED reduces error rates and outperforms standard decoding methods.
We developed a new quantum annealing (QA) algorithm for Dirichlet process mixture (DPM) models based on the Chinese restaurant process (CRP). QA is a parallelized extension of simulated annealing (SA), i.e., it is a parallel stochastic optimization technique. Existing approaches [Kurihara et al. UAI2009, Sato et al. UA…
Recurrent models can produce infinite sequences, causing bias; new methods prevent this.
problem Inconsistency in decoding infinite-length sequences from recurrent language models.
method Defined and proved inconsistency of common decoding algorithms; proposed remedies.
result Proposed methods prevent inconsistency in practice.
In automatic speech recognition (ASR) what a user says depends on the particular context she is in. Typically, this context is represented as a set of word n-grams. In this work, we present a novel, all-neural, end-to-end (E2E) ASR sys- tem that utilizes such context. Our approach, which we re- fer to as Contextual Lis…
Reliable 4D aircraft trajectory prediction, whether in a real-time setting or for analysis of counterfactuals, is important to the efficiency of the aviation system. Toward this end, we first propose a highly generalizable efficient tree-based matching algorithm to construct image-like feature maps from high-fidelity m…
Deep RL learns 2-opt heuristics to improve TSP solutions.
problem Improving TSP solutions beyond initial heuristics.
method Deep reinforcement learning to learn 2-opt operations.
result Learned policies improve solutions faster than previous methods.
Smoothed top-k operator improves model training efficiency.
problem Discontinuous top-k operation makes models untrainable end-to-end.
method SOFT top-k operator approximates top-k as EOT solution.
result Improved performance in k-nearest neighbors and beam search.
Self-taught optimizer improves code generation using language models.
problem Improving code generation using language models.
method Recursive self-improvement of a scaffolding program that generates code.
result Improved scaffolding program generates programs with significantly better performance.
Label smoothing improves model calibration and generalization but harms distillation.
problem Understanding the effects of label smoothing on model calibration and distillation.
method Empirical evaluation and visualization of network representations.
result Label smoothing improves model calibration but harms knowledge distillation.
Exact hierarchical clustering algorithms for data analysis.
problem Finding meaningful structures in data like phylogenetic trees.
method Novel dynamic-programming algorithms based on a trellis data structure.
result Exact computation of partition function, maximum likelihood hierarchy, and marginal probabilities.