VinayReddy Mandati

💥💥💥 Adaptive Decoding via Latent Preference Optimization Shehzaad Dhuliawala, Ilia Kulikov, Ping Yu, Asli Celikyilmaz, Jason Weston, Sainbayar Sukhbaatar, Jack Lanchantin Abstract During language model decoding, it is known that using higher temperature sampling gives more creative responses, while lower temperatures are more factually accurate. However, such models are commonly applied to general instruction following, which involves both creative and fact seeking tasks, using a single fixed temperature across all examples and tokens. In this work, we introduce Adaptive Decoding, a layer added to the model to select the sampling temperature dynamically at inference time, at either the token or example level, in order to optimize performance. To learn its parameters we introduce Latent Preference Optimization (LPO) a general approach to train discrete latent variables such as choices of temperature. Our method outperforms all fixed decoding temperatures across a range of tasks that require different temperatures, including UltraFeedback, Creative Story Writing, and GSM8K. 👉 https://lnkd.in/dvniu3XC #machinelearning

11

3 Comments

💥💥💥 Adaptive Decoding via Latent Preference Optimization Shehzaad Dhuliawala, Ilia Kulikov, Ping Yu, Asli Celikyilmaz, Jason Weston, Sainbayar Sukhbaatar, Jack Lanchantin Abstract During language model decoding, it is known that using higher temperature sampling gives more creative responses, while lower temperatures are more factually accurate. However, such models are commonly applied to general instruction following, which involves both creative and fact seeking tasks, using a single fixed temperature across all examples and tokens. In this work, we introduce Adaptive Decoding, a layer added to the model to select the sampling temperature dynamically at inference time, at either the token or example level, in order to optimize performance. To learn its parameters we introduce Latent Preference Optimization (LPO) a general approach to train discrete latent variables such as choices of temperature. Our method outperforms all fixed decoding temperatures across a range of tasks that require different temperatures, including UltraFeedback, Creative Story Writing, and GSM8K. 👉 https://lnkd.in/dvniu3XC #machinelearning

3

💥💥💥 RieszBoost: Gradient Boosting for Riesz Regression Kaitlyn J. Lee, Alejandro Schuler Abstract Answering causal questions often involves estimating linear functionals of conditional expectations, such as the average treatment effect or the effect of a longitudinal modified treatment policy. By the Riesz representation theorem, these functionals can be expressed as the expected product of the conditional expectation of the outcome and the Riesz representer, a key component in doubly robust estimation methods. Traditionally, the Riesz representer is estimated indirectly by deriving its explicit analytical form, estimating its components, and substituting these estimates into the known form (e.g., the inverse propensity score). However, deriving or estimating the analytical form can be challenging, and substitution methods are often sensitive to practical positivity violations, leading to higher variance and wider confidence intervals. In this paper, we propose a novel gradient boosting algorithm to directly estimate the Riesz representer without requiring its explicit analytical form. This method is particularly suited for tabular data, offering a flexible, nonparametric, and computationally efficient alternative to existing methods for Riesz regression. Through simulation studies, we demonstrate that our algorithm performs on par with or better than indirect estimation techniques across a range of functionals, providing a user-friendly and robust solution for estimating causal quantities. 👉 https://lnkd.in/dCszhVaP #machinelearning

1

🤔 What is a perceptron, and how does it work? --- Get our FREE data science cheat sheets in high resolution by subscribing to our blog today! https://lnkd.in/ejCdvUUA #machinelearning

5

🔍 Enhancing NLP with Retrieval-Augmented Models: The Rise of RAG and RAU In the realm of Natural Language Processing (NLP), integrating external data to refine outputs is reshaping how language models perform. Researchers from East China University of Science and Technology and Peking University have detailed advancements in Retrieval-Augmented Language Models (RALMs), specifically focusing on Retrieval-Augmented Generation (RAG) and Retrieval-Augmented Understanding (RAU). These frameworks are pivotal in addressing the limitations of traditional Large Language Models (LLMs) like hallucinations and the need for domain-specific knowledge. RALMs enhance NLP tasks by pulling relevant external information to support the language model's output, offering solutions in various interaction modes. For instance, sequential interactions involve retrievers identifying relevant documents to inform the model’s predictions, enhancing accuracy. Parallel interactions allow retrievers and language models to operate independently, synchronizing their outputs to optimize results. The versatility of RALMs is supported by diverse retrieval methods—sparse, dense, internet, and hybrid—each tailored to maximize performance across different NLP tasks. Sparse methods use straightforward techniques such as TF-IDF, while dense retrieval employs deep learning to improve accuracy. Hybrid retrieval combines these methods to leverage their strengths comprehensively. The practical applications of RAG and RAU are vast, spanning machine translation, dialogue generation, and text summarization. In dialogue generation, for example, RALMs produce contextually relevant responses in multi-turn interactions, significantly enhancing user engagement and system responsiveness. In summary, the development of RAG and RAU marks a significant step forward in NLP technology, merging external data retrieval with powerful language processing to overcome traditional LLM challenges. This integration not only enhances model performance but also broadens the scope of NLP applications, making it a critical area for future research and development. 👉 Explore the full paper below or download link in the comments below. If you find it valuable, please like and share this post – your engagement shapes the content I share. Also, follow me if you haven't already. Thanks! #NLP #AI #MachineLearning #DataRetrieval #LanguageModels #RAG #RAU

2

2 Comments

#ExplainableAI (XAI) is an emerging subset in #AI that focuses on the readability of #ML models. Want to further understand what #XAI is and how it works? Dive into our blog post: https://hubs.ly/Q02qHJgT0

8

A Multimodal Automated Interpretability Agent Tamar Rott Shaham, Sarah Schwettmann, Franklin Wang, Achyuta Rajaram, Evan Hernandez, Jacob Andreas, Antonio Torralba Abstract This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpretation and failure mode discovery. It equips a pre-trained vision-language model with a set of tools that support iterative experimentation on subcomponents of other models to explain their behavior. These include tools commonly used by human interpretability researchers: for synthesizing and editing inputs, computing maximally activating exemplars from real-world datasets, and summarizing and describing experimental results. Interpretability experiments proposed by MAIA compose these tools to describe and explain system behavior. We evaluate applications of MAIA to computer vision models. We first characterize MAIA's ability to describe (neuron-level) features in learned representations of images. Across several trained models and a novel dataset of synthetic vision neurons with paired ground-truth descriptions, MAIA produces descriptions comparable to those generated by expert human experimenters. We then show that MAIA can aid in two additional interpretability tasks: reducing sensitivity to spurious features, and automatically identifying inputs likely to be mis-classified. 👉 https://lnkd.in/dzE-X6hg #machinelearning

1

Models like OpenAI's CLIP combine text and images for search, but they have limitations, particularly with longer texts and complex relationships. This article talks about JINA's new model that improves on CLIP by integrating both text and image embeddings in one model, making it faster and more efficient for multimodal search tasks. Experiments and Findings: → Search with Both Text and Images: Combining both embeddings leads to better and more diverse search results, improving relevance and variety in results. → Image-Driven Diversification: By using images for diversification, Jina-CLIP v1 can present a broader range of results, offering users more varied options. Results Comparison: → Using both text and image embeddings (via averaging) consistently outperformed searches based solely on text or images, providing more precise and diverse retrieval across both broad and fine-grained categories. https://lnkd.in/guNRQpBU

15

Learn how you can convert a PyTorch model, trained on the web, to a mobile-optimized format. Madhur Zanwar describes the process using a few lines of code. He also discusses his journey and how one approach didn't yield satisfactory results while trying to run it in a React Native app. #machinelearning #pytorch #computervision #edgeml #reactnative #objectdetection #yolov5

14

💥💥💥 Active Data Curation Effectively Distills Large-Scale Multimodal Models Vishaal Udandarao, Nikhil Parthasarathy, Muhammad Ferjad Naeem, Talfan Evans, Samuel Albanie, Federico Tombari, Yongqin Xian, Alessio Tonioni, Olivier J. Hénaff Abstract Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight inheritance. In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining. Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations. Further, we find such an active data curation strategy to in fact be complementary to standard KD, and can be effectively combined to train highly performant inference-efficient models. Our simple and scalable pretraining framework, ACED, achieves state-of-the-art results across 27 zero-shot classification and retrieval tasks with upto 11% less inference FLOPs. We further demonstrate that our ACED models yield strong vision-encoders for training generative multimodal models in the LiT-Decoder setting, outperforming larger vision encoders for image-captioning and visual question-answering tasks. 👉 https://lnkd.in/dNNAhrgw #machinelearning

2

Learn the basics of nonlinear dimensionality reduction, kernel PCA, and multidimensional scaling by following along Biman Chakraborty's clear, hands-on Python tutorial.

18

💥💥💥 Learning How Hard to Think: Input-Adaptive Allocation of LM Computation Mehul Damani, Idan Shenfeld, Andi Peng, Andreea Bobu, Jacob Andreas Abstract Computationally intensive decoding procedures--including search, reranking, and self-critique--can improve the quality of language model (LM) outputs in problems spanning code generation, numerical reasoning, and dialog. Existing work typically applies the same decoding procedure for every input to an LM. But not all inputs require the same amount of computation to process. Can we allocate decoding computation adaptively, using more resources to answer questions whose answers will be harder to compute? We present an approach that predicts the distribution of rewards given an input and computation budget, then allocates additional computation to inputs for which it is predicted to be most useful. We apply this approach in two decoding procedures: first, an adaptive best-of-k procedure that dynamically selects the number of samples to generate as input to a reranker; second, a routing procedure that dynamically responds to a query using a decoding procedure that is expensive but accurate, or one that is cheaper but less capable. Across a suite of programming, mathematics, and dialog tasks, we show that accurate computation-allocation procedures can be learned, and reduce computation by up to 50% at no cost to response quality, or improve quality by up to 10% at a fixed computational budget. 👉 https://lnkd.in/d7_mGJKF #machinelearning

2