Picture for Aditya Desai

Aditya Desai

IDentity with Locality: An ideal hash for gene sequence search

Add code
Jun 21, 2024
Viaarxiv icon

Heterogeneous federated collaborative filtering using FAIR: Federated Averaging in Random Subspaces

Add code
Nov 03, 2023
Viaarxiv icon

In defense of parameter sharing for model-compression

Add code
Oct 17, 2023
Figure 1 for In defense of parameter sharing for model-compression
Figure 2 for In defense of parameter sharing for model-compression
Figure 3 for In defense of parameter sharing for model-compression
Figure 4 for In defense of parameter sharing for model-compression
Viaarxiv icon

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

Add code
May 26, 2023
Viaarxiv icon

The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model

Add code
Jul 21, 2022
Figure 1 for The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model
Figure 2 for The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model
Figure 3 for The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model
Figure 4 for The trade-offs of model size in large recommendation models : A 10000 $\times$ compressed criteo-tb DLRM model
Viaarxiv icon

Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing

Add code
Jul 21, 2022
Figure 1 for Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing
Figure 2 for Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing
Figure 3 for Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing
Figure 4 for Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing
Viaarxiv icon

Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\times$ Compression and 2.7$\times$ Faster Inference

Add code
Aug 04, 2021
Figure 1 for Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\times$ Compression and 2.7$\times$ Faster Inference
Figure 2 for Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\times$ Compression and 2.7$\times$ Faster Inference
Figure 3 for Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\times$ Compression and 2.7$\times$ Faster Inference
Figure 4 for Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\times$ Compression and 2.7$\times$ Faster Inference
Viaarxiv icon

Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion

Add code
Feb 26, 2021
Figure 1 for Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion
Figure 2 for Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion
Figure 3 for Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion
Figure 4 for Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion
Viaarxiv icon

Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems

Add code
Feb 24, 2021
Figure 1 for Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems
Figure 2 for Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems
Figure 3 for Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems
Figure 4 for Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems
Viaarxiv icon

Density Sketches for Sampling and Estimation

Add code
Feb 24, 2021
Figure 1 for Density Sketches for Sampling and Estimation
Figure 2 for Density Sketches for Sampling and Estimation
Figure 3 for Density Sketches for Sampling and Estimation
Figure 4 for Density Sketches for Sampling and Estimation
Viaarxiv icon